Wähle aus 56 verfügbaren Integrationen und 716 nativen Actions, um deine Agenten und Workflows zu erweitern.
Actions
Create comment
Adds a comment to a record. Requires a base ID, table name, record ID, and the comment text. Returns the created comment.
Create records
Creates one or more records in a table. Requires a base ID, table name, and an array of field values. Returns the created records with their IDs.
Delete record
Deletes a record from a table. Requires a base ID, table name, and record ID. Returns confirmation of deletion.
Find records
Searches for records in a table with optional filtering. Requires a base ID and table name. Always call Get table schema first to get the exact field names. Returns matching records with their fields.
Get base schema
Returns all tables and their fields for a base. Requires a base ID. Returns table names, field names, types, and select options.
Get record
Fetches a single record by its ID. Requires a base ID, table name, and record ID. Returns the record's fields and metadata. Optionally resolves linked records into full objects.
Get table schema
Returns the field names, types, and options for a single table. Requires a base ID and table ID. Call this before searching or creating records to know the exact field names.
List comments
Lists all comments on a record. Requires a base ID, table name, and record ID. Returns comments with author and timestamp.
Triggers
Actions
Add task followers
Adds followers to a task so they receive update notifications. Requires a task GID from search_tasks or typeahead_search and follower user GIDs from get_users. Returns the updated followers list
Create project
Creates a new project in Asana. Requires a project name. Optionally accepts workspace GID from list_workspaces, team GID from get_teams_for_workspace, owner, color, privacy settings, and dates. Returns the created project with its GID
Create task
Creates a new task in Asana. Requires a task name. Optionally accepts workspace GID from list_workspaces, project GID from get_projects, assignee from get_users, due dates, and custom fields. Returns the created task with its GID
Create task story
Adds a comment to a task. Requires the comment text and a task GID from search_tasks or typeahead_search. Returns the created comment
Download attachment
Gets detailed attachment data including name, download URL, view URL, and parent resource. Requires an attachment GID from get_attachments_for_object. Returns complete attachment information needed for accessing the file
Download attachments for object
Downloads all attachments for a project, task, or project brief as base64-encoded files. Requires a parent GID from typeahead_search. Returns file names, MIME types, and base64 content
Get attachments for object
Lists attachment metadata (names, types, IDs) for a project, task, or project brief without downloading file content. Requires a parent GID from typeahead_search. Returns attachment GIDs, names, and resource types
Get goal
Gets detailed goal data including due dates and owner. Requires a goal GID from get_goals. Returns full goal details
Get goals
Lists goals in a workspace, optionally filtered by team, project, portfolio, or owner. Requires a workspace GID from list_workspaces. Returns goal GIDs, names, and owners
Get parent goals for goal
Lists all parent goals for a specific goal. Requires a goal GID from get_goals. Returns parent goal GIDs and names
Get portfolio
Gets detailed portfolio data including owner, members, and custom fields. Requires a portfolio GID from get_portfolios. Returns full portfolio details
Get portfolio items
Lists items (projects) in a portfolio. Requires a portfolio GID from get_portfolios. Returns item GIDs, names, and resource types
Get portfolios
Lists portfolios filtered by owner, workspace, or team. Requires an owner user GID from get_users. Optionally accepts workspace GID from list_workspaces and team GID from get_teams_for_workspace. Returns portfolio GIDs and names
Get project
Gets detailed project data including dates and owner. Requires a project GID from get_projects. Returns full project details
Get projects
Lists projects in a workspace, optionally filtered by team. Requires a workspace GID from list_workspaces. Returns project GIDs and names
Get projects for team
Lists all projects for a specific team. Requires a team GID from get_teams_for_workspace. Returns project GIDs and names
Get projects for workspace
Lists ALL projects in a workspace across all teams. Requires a workspace GID from list_workspaces. Returns project GIDs, names, and resource types
Get project task counts
Gets task count statistics for a project (total, completed, incomplete, milestones). Requires a project GID from get_projects. Returns task counts by status
Get stories for task
Gets task activity history including comments, status changes, and system events. Requires a task GID from search_tasks or typeahead_search. Returns stories with text, author, and timestamps
Get story
Gets a single story (comment or event) by its GID. Requires a story GID from get_stories_for_task. Returns the full story details
Get tags in workspace
Lists all tags in a workspace. Requires a workspace GID from list_workspaces. Returns tag GIDs and names
Get task
Gets full task details including assignee, dates, custom fields, and memberships. Requires a task GID from search_tasks or typeahead_search. Returns complete task data
Get tasks
Lists tasks filtered by project, section, tag, workspace, or user task list. Requires at least one context filter (e.g. a project GID from get_projects). Returns task GIDs and names
Get teams for user
Lists teams a user belongs to within an organization. Requires a user GID from get_users and an organization GID from list_workspaces. Returns team GIDs and names
Get teams for workspace
Lists all teams in a workspace. Requires a workspace GID from list_workspaces. Returns team GIDs and names
Get user
Gets detailed user information. Accepts a user GID, email address, or "me" for the authenticated user. Returns name, email, photo, and workspace memberships
Get users
Lists users in a workspace, optionally filtered by team. Requires a workspace GID from list_workspaces. Returns user GIDs, names, and emails
List workspaces
Lists all workspaces and organizations accessible to the authenticated user. No inputs required. Returns workspace GIDs, names, and whether each is an organization
Remove task followers
Removes followers from a task to stop their update notifications. Requires follower user GIDs from get_users and a task GID from search_tasks or typeahead_search. Returns the updated followers list
Search tasks
Advanced task search with filters for text, assignee, dates, completion status, projects, tags, sections, and custom fields. Requires a workspace GID from list_workspaces. Use the text parameter to search by task name. Returns matching task GIDs and names
Set parent for task
Converts a task to a subtask or changes its parent task. Requires the task GID and parent task GID, both from search_tasks or typeahead_search. Returns the updated task
Set task dependencies
Sets tasks that this task depends on (prerequisites that must be completed first). Requires the task GID and dependency task GIDs from search_tasks or typeahead_search. Returns the dependency list
Set task dependents
Sets tasks that are blocked by this task (tasks waiting on this one to complete). Requires the task GID and dependent task GIDs from search_tasks or typeahead_search. Returns the dependent list
Triggers
Actions
Get application info
Fetch application details by application id or by submitted form instance id (which is return by the applicationForm.submit endpoint).
List application feedback
List all interview scorecards and feedback submissions associated with an application.
List criteria evaluations
Fetch a paginated list of AI criteria evaluations for an application. This endpoint returns the AI-generated criteria evaluations that assess how well a candidate meets specific job requirements.
List interview events
List individual calendar meetings (with times, locations, interviewers) within an interview schedule. Use this to see actual calendar events for a specific schedule.
List interviews
List all interview templates/types defined for jobs (e.g., 'Technical Screen', 'Culture Fit'). These are interview definitions, not scheduled interviews.
Actions
Add work item comment
Adds a comment to an Azure DevOps work item using the long-lived preview Comments API.
Commit files
Pushes an atomic commit containing one or more file changes (create, edit, or delete) to an Azure DevOps Git branch.
Create branch
Creates a new Git branch in an Azure DevOps Git repository from an existing branch or commit SHA.
Create pull request
Creates an Azure Repos pull request to review and merge changes between branches.
Create wiki page
Creates a new Markdown page in an Azure DevOps wiki without replacing an existing page.
Create work item
Creates a work item in a project. Use list_work_item_types to see valid types such as User Story, Bug, Task, or Feature.
Get pull request
Gets an Azure Repos pull request by project, repository, and ID, or by pasting a pull request URL.
Get work item
Gets a work item by ID or URL, including description, state, assignee, and attachment metadata.
Get work item comments
Lists comments on an Azure DevOps work item using the long-lived preview Comments API.
Get work item type schema
Discovers fields, required values, allowed values, and states for an Azure DevOps work item type.
List projects
Lists Azure DevOps projects in the connected organization that the signed-in user can access.
List sprints
Lists iterations (sprints) for a team in a project, including the current sprint when one is set.
List work item types
Lists work item types available in a project, such as User Story, Bug, Task, and Feature.
Merge pull request
Submits a completion (merge) request for an Azure Repos pull request into its target branch.
Actions
Get resource
Gets one Azure control-plane resource by its full ARM resource ID. Returns identity, sku, tags, and the resource properties bag with secret-named keys and SAS-like values removed. Does not GET app settings, keys, or other secret-bearing child paths.
List activity logs
Lists Azure Activity Log management events for a subscription. Returns caller, time, status, localized operation, ARM operation ID (for example Microsoft.Network/networkSecurityGroups/securityRules/write), and category. Filters by time range and optionally one of resource ID, resource group, resource provider, or correlation ID. Defaults to 50 events, maximum 200. Azure next-page tokens are followed internally and are not exposed. Activity Log does not include property diffs; use List resource changes for before/after values.
List resource changes
Lists Azure Resource Graph change-history rows (the portal Change history table). Returns change type, time, target resource, ARM operation, changedBy when present, correlation ID, and property diffs. This is not Activity Log: diffs live here, caller/time audit lives in List activity logs; join them with correlation ID. Retention is about 14 days. Create events often have an empty changes bag. Child resources such as NSG rules usually appear as diffs on the parent resource. Nested types that are not in Resource Graph will not appear. Azure skip tokens are followed internally up to the row limit; there is no page token.
List resource groups
Lists Azure resource groups the signed-in user can see, ordered by name. Omit subscription ID to search across accessible subscriptions. Always uses Azure Resource Graph so the type and sort stay the same whether a subscription ID is passed or not.
List subscriptions
Lists Azure subscriptions the signed-in user can access through Azure Resource Manager.
Query resources
Runs a Kusto query against Azure Resource Graph and returns matching control-plane resources. Azure skip tokens are followed internally up to the row limit; this action does not accept a page token.
Search resources
Searches Azure Resource Graph for control-plane inventory: id, name, type, resource group, location, subscription, and tags. It does not return the ARM properties bag. For SKU, identity, network rules, capacity admins, and other details of one resource, call Get resource with that id. Filters run in Azure; at most 200 rows (default 50); no page token. Omit name and type to list resources the signed-in user can see. Use Query resources only when the user already has KQL against ARG tables. Nested types (Microsoft.Search/searchServices/indexers) are usually not in Resource Graph; search the parent type instead. Does not search resource groups; use List resource groups for those.
Triggers
Actions
Actions
Add comment
Adds a comment to a Confluence page. Supports @mentions (resolved to real people if found, otherwise kept as plain text) and replies to existing comments.
Append to page
Appends plain text or storage XHTML to the bottom of an existing Confluence page while preserving all existing content, macros, layouts, and embedded image attachments untouched. Select the content format explicitly. Use this for adding new sections, meeting notes, logs, or updates without rewriting the page. For modifying existing text in place, use replace_page_text; for rewriting the entire page, use update_page.
Download attachment
Downloads a file attached to a Confluence page or blog post. Use the list attachments action first to get the attachment ID.
Get page
Retrieves a Confluence page's content and metadata, including its parent and immediate children. Returns cleaned XHTML in bodyContent by default. Set includeRawBody=true when using replace_page_text or rewriting a page that contains storage metadata, then pass the unmodified rawBodyContent to the relevant action so metadata is preserved. Pass bodyContent to update_page only when metadata preservation is not needed. For adding content at the bottom without rewriting, use append_to_page. Set removeHTMLTags=true for plain text output.
Get page hierarchy
Lists pages under a Confluence page recursively. Filters out folders and whiteboards.
Get pages
List pages using structured filters such as space, status, sort order, or specific page IDs. Best for browsing or listing pages rather than matching by text.
List attachments
Lists the files attached to a Confluence page or blog post, with their IDs, names, and sizes. Use this to see what files are on a page, or to get an attachment ID to pass to the download attachment action.
Replace page text
Replaces a specific text snippet, paragraph, or section in an existing Confluence page while preserving all other page content, macros, layouts, and embedded image attachments untouched. Call get_page with includeRawBody=true and use its exact rawBodyContent for findText so storage metadata remains intact. Plain-text replacements are XML-escaped automatically; set Replace text format to storage XHTML when replacing markup. Use this for targeted in-place edits. For adding new content at the bottom without changing existing text, use append_to_page; for rewriting the entire page, use update_page.
Search
Search Confluence pages by keyword, phrase, or partial title, or paste a Confluence page URL to open that page directly. Searches page titles and body text across every space unless narrowed. Optionally filter by space (spaceKeys), label, or date range (lastModifiedAfter/Before, createdAfter/Before). To find the pages nested under a specific page, set the parent page filter (ancestorId) rather than putting an ancestor or parent term in the query. Each hit includes immediateParent (the page directly above it) and parent (the top of the ancestor chain — kept for compatibility; prefer immediateParent when asking what a page sits under).
Update blog post
Updates an existing Confluence blog post's title, body, or status. Blog posts are a separate content type from pages, so this action handles them, not the update page action.
Update comment
Updates an existing comment on a Confluence page. Supports @mentions (resolved to real people if found, otherwise kept as plain text).
Update page
Updates an existing Confluence page by ID. For adding new content at the bottom without rewriting, use append_to_page. For a targeted edit to a sentence, paragraph, or section, use replace_page_text instead so the rest of the page (including embedded images) is left untouched. Set titleChangeOnly=true to rename only (no version number needed). Set titleChangeOnly=false to rewrite the full page body. Full-body updates stop when bodyContent omits any existing embedded image reference.
Actions
Add comment
Adds a comment to a Confluence page. Can also reply to an existing comment by providing a parent comment ID.
Create page
Creates a new page in a Confluence space. Use this when users want to create new content, add a page, or publish information to Confluence.
Get comments
Retrieves comments for a Confluence page with their reply hierarchy. Returns comments with nested replies, including author information and timestamps.
Get page
Retrieves a specific Confluence page by its ID and returns a clean text-only body plus basic metadata (URL, title, timestamps). Always includes references (id, title, url) to the page's direct sub-pages; optionally also returns the sub-pages' full content.
Get pages
Gets pages using structured filters like space, status, or sorting. Use this when users want to list/browse pages from specific spaces, get recent pages, or filter by criteria
Get spaces
Lists all spaces in the Confluence workspace. Use this action when the user asks for available spaces, or when you need to look up a space ID by name or key before calling other actions.
Actions
Ask Genie
Asks a Genie agent a natural-language question about its configured data. Starts a new conversation or continues an existing one.
Get dashboard
Reads a Databricks (Lakeview) dashboard's metadata, its underlying SQL queries, and page structure. Accepts a dashboard ID or a dashboard URL.
Get Genie response
Gets a Genie response that was still processing when Ask Genie returned. Returns the answer, generated queries, and query results when ready.
Get notebook
Gets the source content of a Databricks notebook. Accepts a workspace path or a notebook URL of the .../#workspace/<path> form.
Get SQL result
Fetches the status and result of a SQL query that was submitted with 'Run SQL query'. Use this to check back on a query that was still running.
Get table metadata
Retrieves detailed metadata for a specific table including description, columns with their types and comments, owner, and tags. Essential for data discovery.
Invoke agent
Sends a message to a Databricks agent serving endpoint and returns the agent's response. Supports supervisor agents and any chat-based serving endpoint.
List catalogs
Lists all Unity Catalog catalogs accessible to the user. Catalogs are the top-level container for data assets.
List dashboards
Lists the Lakeview dashboards in the workspace. Use 'Get dashboard' on a returned dashboard ID to read its queries and structure.
List Genie agents
Lists the Genie agents available in the workspace. Genie agents answer natural-language questions about data in Unity Catalog.
List notebooks
Lists the notebooks, files, and folders directly under a workspace path. Use 'Get notebook' on a returned notebook path to read its content.
List schemas
Lists all schemas within a specified catalog. Schemas contain tables, views, and other data objects.
List serving endpoints
Lists all model serving endpoints in the workspace, including agent endpoints. Shows endpoint name, state, and type.
List SQL warehouses
Lists the SQL warehouses in the workspace. Use this to find the warehouse to run SQL statements against.
List tables
Lists all tables within a specified catalog and schema. Returns table names, types, and basic metadata.
List volumes
Lists all volumes within a specified catalog and schema. Volumes are used to store unstructured data like files.
Triggers
Actions
Get usage
Retrieves current usage information for your DeepL API account including character counts and limits.
Improve text
Improves and rephrases text in the specified target language with optional writing style or tone but not both.
Triggers
Actions
Create table
Creates a new table from a cell range. Tables enable filtering, sorting, and structured references.
Get range
Retrieves data from a specified cell range in a worksheet. Use this to read data that is not in a table.
Get table rows
Retrieves rows from a table with pagination support, including the table name. Use this to read data from Excel tables.
Get workbook summary
Retrieves a summary of an Excel workbook including all sheets, their data ranges, tables, and charts.
Insert column
Inserts a new empty column to the left or right of a specified column, shifting existing columns.
Insert formulas
Inserts Excel formulas into cells at a specified range. Use this to add calculations like =SUM(), =AVERAGE(), =IF(), etc.
Triggers
Actions
Change file
Creates a new file or updates an existing file in a repository. For new files, provide the path and content. For existing files, also provide the current file SHA (from get_file_content or get_repository_content) to update it.
Compare
Compares two branches, tags, or commits and shows the diff. Returns commits, changed files with patches, and stats. Use for release diffs, PR previews, or any ref comparison.
Get branch
Retrieves detailed information about a specific branch, including protection status and latest commit.
Get commit diff
Gets diff information for a specific commit. Returns file stats (files changed, additions, deletions) and optionally the detailed patch content for each file.
Get current user
Retrieves the profile of the authenticated GitHub user, including login, name, email, and account statistics.
Get file content
Retrieves the actual content of a file from a repository. Use get_repository_content first to find the file path, then use this action to read its contents.
Get release
Retrieves detailed information about a specific release by its ID, including release notes and downloadable assets.
Get release by tag
Retrieves detailed information about a release by its tag name (e.g., v1.0.0). More intuitive than ID lookup when the tag is known.
Get repository content
Lists files and directories in a repository path. Use this to browse the structure of a repository before retrieving specific files.
List branches
Lists all branches in a repository. Useful for branch selection in workflows or checking available branches before operations.
List releases
Lists all releases in a repository. Useful for changelog automation, docs sync, and tracking deployments.
Search code
Searches for code and files across GitHub repositories. Use 'filename' to find files by name (e.g., schema.prisma, package.json). Use 'query' to search for text INSIDE file contents. You can combine both. Always specify owner and repository when searching within a specific repo for best results.
Actions
Create merge request
Creates a merge request from a source branch into a target branch. Requires a token with api scope.
Get current user
Retrieves the profile of the authenticated GitLab user, including id, username, name, and email.
Get file content
Retrieves the raw text content of a file in a project's repository. Use Get repository content first to find the path.
Get merge request
Retrieves a single merge request by its project-scoped IID, optionally including its commits and pipelines.
Get merge request diffs
Gets the changed files and diffs for a merge request, by its project-scoped IID.
Get repository content
Lists files and directories at a path in a project's repository tree. Use this to browse structure before reading a file.
List commits
Lists commits in a project's repository, newest first, optionally filtered by branch, path, or date range.
List projects
Lists GitLab projects you are a member of by default. Returns id, path, name, and visibility for each project. Use Membership to list owned projects or any accessible projects.
Manage pipeline
Creates, retries, or cancels a CI/CD pipeline in a project. Requires a token with api scope.
Merge merge request
Merges an open merge request into its target branch. Requires a token with api scope. Fails if the MR is not mergeable (conflicts, missing approvals, or failing required checks).
Actions
Get email with attachments
Retrieves a single email thread or message with full content including attachments. Returns all messages in the thread and their attachment files.
List labels
Lists all labels in the user's mailbox. Agents can call this to find the correct label ID when a user mentions a label name that can't be resolved.
Search emails
Searches through your Gmail inbox and returns email summaries (subject, sender, date, snippet) matching your search criteria. Use 'Get email with attachments' to retrieve full email content.
Triggers
Actions
Analyze content performance
Specialized report for analyzing page/content performance to identify high and low performers, detect anomalies, and understand topic effectiveness.
Analyze traffic sources
Analyze traffic sources, acquisition channels, and marketing performance to detect anomalies and identify effective channels.
Batch run reports
Generate multiple custom reports in a single API call for efficient data analysis and comparison.
Get metadata
Retrieve all available dimensions and metrics for the property, including custom dimensions and metrics.
Get realtime users by device
Retrieves active users in the last 30 minutes broken down by device category (desktop, mobile, tablet).
Triggers
Actions
Actions
Add header or footer
Creates a header or footer in a Google Docs document and optionally populates it with text
Append text
Appends plain text to the end of a Google Docs document or a specific tab without any formatting conversion
Create document
Create a new Google Docs document with a title and optionally place it in a specific folder.
Format text
Applies formatting styles like bold, italic, underline, font size, or color to all occurrences of a text string in a Google Docs document
Insert table
Creates a table with headers and data rows in a Google Docs document. Headers are automatically bolded.
List tabs
Retrieves a list of all tabs in a Google Doc with their IDs, names, and positions. Use this to discover available tabs before retrieving specific tab content.
Triggers
Actions
Copy file
Creates a copy of an existing file in Google Drive with optional new name, destination folder, and description.
Create folder
Creates folders in Google Drive. Supports multiple folders (comma-separated) and nested paths (using '/'). If a folder already exists, it will be reused and the user notified.
Get file metadata
Retrieves detailed metadata for a file by its ID including name, type, size, dates, and owner information.
List folders
Lists folders to help navigate your Google Drive. Without a folder, returns your top-level folders and your shared drives; with a folder, returns the folders directly inside it. Use a returned folder ID with Search files or List files in folder to look inside it.
Move file
Moves a file to a different folder in Google Drive. The file is removed from its current folder and placed in the target folder.
Actions
Append rows to spreadsheet
Appends new rows to the end of a spreadsheet, automatically finding the last row with data.
Clear spreadsheet rows
Clears the content of the selected rows while keeping the rows intact in the workspace.
Download spreadsheet
Download a spreadsheet as an Excel (.xlsx) file to read, filter, or sort large sheets.
Get comments
Retrieves threaded comments (not cell notes) and their replies from a Google Sheets spreadsheet. Use this to read collaborative feedback, review notes, or discussion threads left by collaborators on the spreadsheet.
Actions
Add image
Inserts an image from a publicly accessible URL onto a slide at a given position and size. Use it to add logos, photos, charts, or other pictures to an existing slide. Requires the target presentationId and the slide's object ID (slideId); returns the created image's object ID as imageId, which you can reference in later calls to move, resize, or replace the image.
Add line
Draws a line, arrow, or connector on a slide. Use it to add a straight/bent/curved line, a directional arrow, or a connector that visually links two existing shapes. Provide the slide's object ID (from get_presentation or a create action) as slideId; the line's own object ID is returned as lineId for later reference. To connect endpoints to shapes, pass those shapes' existing object IDs in startConnectionId/endConnectionId.
Add shape with text
Creates a shape or text box (optionally pre-filled with text) on a specific existing slide; use it to add text content, containers, callouts, arrows, or diagram elements to a deck. ID flow: takes the presentation's ID and the target slide's OBJECT ID (not its number), and returns the created shape's object ID as shapeId — capture it to format, move, or modify the shape in later calls.
Add table
Creates a new table with the given rows/columns at a position on a slide, optionally pre-filling and formatting cells via initialData in one call. Use it to add comparison/data grids to a deck. Needs the presentationId and the target slide's object ID; returns the created table's object ID (tableId) — pass that to later actions (e.g. updating cells or styling) to reference this table.
Batch update (advanced / raw API)
Power escape hatch: send a raw array of Google Slides API requests in one ATOMIC presentations.batchUpdate call. Use this ONLY for advanced or rarely-needed operations the dedicated actions (Create slide, Add table, Add image, Add shape with text, Edit shape text, Replace text, Update text style, Update paragraph style, Update shape properties, Update element transform, Add line, Duplicate object) do NOT cover - e.g. reordering or deleting slides (updateSlidesPosition, deleteObject), grouping/ungrouping, bullet/numbered lists (createParagraphBullets), z-ordering (updatePageElementsZOrder), merging table cells, recoloring images, embedding Sheets charts (createSheetsChart), updating slide/page background or page properties, or any brand-new request type. Prefer the dedicated actions when one fits. ID flow: every request that targets an EXISTING slide or element (its 'objectId' / 'pageObjectId') needs that element's exact opaque object ID - get it from get_presentation (outputFormat 'map' for a compact slideId index, or 'json'), or from the id returned by the action that created it; NEVER pass a slide number or an invented name. To name a NEW object yourself, set 'objectId' inside the create request (5-50 chars of letters/digits/'_'/'-'/':', not starting with a digit, unique in the deck); omit it to auto-generate. IMPORTANT: batchUpdate is ATOMIC - if any single request is invalid the ENTIRE batch is rejected and NOTHING is applied (the deck stays unchanged), so fix the one bad request and resend the whole batch. The response returns the raw replies plus a positional reply summary and a map of newly-created object IDs (requestIndex to resulting objectId) so you can chain follow-up requests without a separate GET. PREFER the dedicated actions for common edits (e.g. update_slide_background, update_z_order, update_shape_properties, update_table, create_slide, add_image) — they build the exact Slides API request for you; use batch_update only for operations without a dedicated action or to apply many edits in one atomic call. Schema notes: a solidFill color takes rgbColor directly (NO 'opaqueColor' wrapper), and updatePageElementsZOrder uses 'pageElementObjectIds' (not 'pageObjectIds'). These two common mistakes are auto-corrected, but other request fields must match the Google Slides API exactly.
Build deck from outline
Build a complete multi-slide deck from a structured outline in one operation: pass an array of slide specs (each a layout plus optional title, body, speaker notes, and a custom objectId) and it creates every slide with the right layout, fills the title/body placeholders, auto-bullets list bodies, and sets speaker notes. Use this to turn a whole outline into a finished deck in a single call; use create_slide only to add one slide. Requires an existing presentation (create one first with create_presentation). ID flow: returns slideIds (the slide OBJECT IDs it used) and, per slide, the title/body placeholder objectIds and notesObjectId — reference those exact returned IDs in later edits instead of guessing.
Copy presentation
Duplicates an existing Google Slides presentation into a new file (optionally renamed and placed in a specific Drive folder); use it to clone a deck before editing or to spin up a copy from a template. Returns the new presentation's ID as newPresentationId — pass that ID to subsequent actions (get_presentation, create_slide, etc.) when working on the copy.
Create presentation
Create a new blank Google Slides presentation (with one default slide) and optionally place it in a specific Drive folder; use this to start a new deck before adding slides or content. Returns the new presentationId (the ID needed by every other Google Slides action) plus the object ID of the initial slide, so capture them from the result and pass them to later calls rather than guessing.
Create slide
Add a new slide to a presentation with a chosen layout and, optionally, fill its title and body placeholders in the same step (no separate text action needed). Use it whenever you need to insert a slide into an existing deck. IDs: pass the target presentation's ID in presentationId; the action RETURNS the new slide's object ID (slideId) plus the auto-assigned title and body placeholder object IDs (titlePlaceholderId, bodyPlaceholderId, placeholderIds), which you should reuse to style or further edit those elements without re-fetching the presentation.
Create video
Embeds a YouTube or Google Drive video onto a slide in one step; use it to add a video player (YouTube is the common case) to an existing slide. ID flow: pass the target slide's OBJECT ID in slideId (not its number) and the presentation's ID in presentationId; the video's source id goes in `id`. Returns the created video element's object ID (as both objectId and videoObjectId) so you can immediately reposition, resize, or delete it without re-fetching the presentation.
Delete object
Permanently deletes one or more slides and/or page elements (shapes, text boxes, images, tables, lines, charts) from a presentation by their object IDs, in a single atomic batch. Use it to undo or fix mistakes - e.g. remove a wrongly placed image, an extra slide, or a stray text box; deleting a slide also removes every element on it. Every ID you pass must be the exact object ID of something that already exists: get slide object IDs from get_presentation with outputFormat "map" (or the slideId/slideIds returned by create_slide / build_deck_from_outline), and element object IDs from the create_* action that made the element or from get_presentation (outputFormat "map" or "json"). Never invent an ID or pass a slide number. The batch is atomic: if any ID is invalid or missing, the whole call is rejected and nothing is deleted.
Duplicate slide or element
Duplicate an existing slide (with all its content) or a single page element (shape, text box, table, image, or line) within the same presentation; the copy is inserted directly after the original. Use it for templating - build one polished slide, then duplicate it per section and customize each copy. ID flow: pass the OBJECT ID of the slide/element to duplicate (from get_presentation or the action that created it). The API auto-generates new IDs for the copy and its children and only returns the new top-level ID, so optionally supply idMappings to assign your own predictable IDs and edit the copy immediately without a follow-up get_presentation. Returns the new top-level object ID plus the full old-to-new ID map.
Edit shape text
Edits the text of an existing shape, text box, or table cell on a slide — replace all text, replace a specific character range, or insert text at a position. Use it to fill placeholders or update copy after a shape exists. You must pass the element's exact object ID in `elementId`: get it from the action that created the element (add_shape_with_text, add_table, etc., which return the id they used) or from get_presentation (outputFormat "map" or "json"). Never invent an ID and never pass a slide number.
Edit speaker notes
Write, append to, or clear the speaker notes for one slide (the presenter-facing 'Notes' area below the slide), not the visible on-slide text. Use it to draft what the presenter should say, add talking points to a slide you just created, or wipe outdated notes. Operates on a single slide identified by its slide OBJECT ID. ID flow: pass the presentationId from the URL and the slide's objectId (from create_slide / build_deck_from_outline output, or get_presentation outputFormat 'map'); the action automatically locates the speaker-notes shape on that slide, so you never supply the notes shape ID yourself.
Embed Sheets chart
Embed an existing chart from a Google Sheets spreadsheet onto a slide as either a LINKED chart (stays connected to the Sheet so it can be refreshed with the latest data) or a NOT_LINKED_IMAGE (a static, non-refreshable snapshot). Use it to drop a Sheets-built chart into a deck instead of recreating the data in Slides. You must have at least view access to the source spreadsheet (the Slides API reads it on your behalf). ID flow: pass the presentationId from the URL, the slide's OBJECT ID (not its number — get it from get_presentation outputFormat "map", or from create_slide / build_deck_from_outline), the spreadsheetId, and the INTEGER chartId from inside that Sheet (0, 1, 2, …) — NOT a Slides object ID. Returns the embedded chart's object ID (objectId / chartObjectId) and whether it is linked, so you can later refresh, move, resize, or delete it.
Export presentation
Export an entire Google Slides deck as a downloadable file and return it to the user — PDF (preserves exact layout/visuals; best for sharing or printing), PPTX (editable PowerPoint), or TXT (plain-text extraction of all slide text). Use this when the user wants to download, save, share, or convert a whole deck. The file is named after the presentation title (e.g. 'My Deck.pdf'). This action consumes only the presentationId (no slide or element IDs); take the presentationId from the URL or from the presentationId returned by create_presentation / copy_presentation. Note: Google's Drive export endpoint caps exports at 10MB — very large decks return an actionable error suggesting TXT or a manual download.
Get presentation
Read a Google Slides presentation's content as a slide map, full JSON, markdown, or plain text. This is the primary way to discover the OBJECT IDs you need for every edit: use outputFormat "map" to get a compact, ID-annotated index (per slide: slideId, layout, title, hasBody, and elementIds), then pass those exact IDs to edit/create actions. Use it before editing to locate slides and elements by ID, and after editing to verify the result. Never guess IDs or use slide numbers — read them from here.
Group objects
Combine two or more existing page elements on the SAME slide (shapes, text boxes, images, lines, word art) into a single group so they move, scale, rotate, and delete together as one unit. Use it to keep related elements locked together (a logo plus its caption, a chart plus its labels) so they stay aligned during later edits. ID flow: you pass the object IDs of elements that ALREADY exist (each create action returns the id it used; get_presentation also lists them), and this action RETURNS the new group's objectId — use that returned id as the chainable handle for follow-up actions (e.g. update_element_transform to move the whole group, or delete_object to remove it). Videos, tables, and placeholders CANNOT be grouped, and all children must be on the same slide and not already part of another group.
List layouts
Inspect a presentation's theme and layout catalog before creating or editing slides. For every layout it returns the predefinedLayout name (the exact value create_slide expects in its layout/predefinedLayout field — e.g. TITLE_AND_BODY), a human display name, and the placeholder types and indices that layout offers (e.g. TITLE[0], BODY[0]) so you never target a placeholder that doesn't exist. Also returns the master's theme color scheme as hex, the slide dimensions (pageSize) in points, and — when the master's placeholder shapes carry styling — the default fonts/styles per placeholder type (defaultTextStyles may be empty for decks whose master placeholders are blank prompt shapes). This action reads only; it consumes a presentationId and produces no object IDs you must thread into later calls — its purpose is to tell you which predefinedLayout names and placeholder slots are valid inputs for create_slide. Use it first whenever you need to know which layouts exist, what placeholders a layout has, or what colors/fonts the theme uses.
List presentations
Find Google Slides presentations the user can access, returning each one's presentationId, name, last-modified/created time, owners, and links. Use it to discover a deck before reading or editing it. This is the entry point for the ID chain: the returned presentationId (the alphanumeric ID in a deck's URL between '/d/' and '/edit') can be passed directly to get_presentation, create_slide, and other Slides actions — so call this first instead of guessing a presentationId. It does not read slide contents or slide/element object IDs; use get_presentation (outputFormat "map") for those.
Refresh linked chart
Re-fetches a linked Google Sheets chart embedded on a slide and updates its image in place so it reflects the current spreadsheet data; use it after the source Sheet's data changes (e.g. to refresh a revenue or KPI chart before presenting). Only charts inserted with a live spreadsheet link (linkingMode LINKED) can be refreshed - a chart pasted as a static image is not linked and returns an actionable error. The chart's objectId is unchanged by the refresh, so it stays addressable for follow-up calls. ID flow: supply the presentationId from the URL and the chart's objectId, which you get from the action that inserted the chart (it returns the id it used) or from get_presentation - never invent or guess it.
Render slide
Renders a slide (or the whole deck) to a PNG image and returns a temporary image URL, width, and height per slide — use it after creating or editing slides to visually verify layout, overflowing text, overlapping elements, colors, and alignment before considering the deck done. Consumes existing IDs only: pass the presentationId from the deck's URL and, optionally, real slide OBJECT IDs (not slide numbers). Leave the slide ID empty to render every slide in order; the contentUrl links it returns expire ~30 minutes after rendering, so view them promptly or re-run.
Reorder slides
Move one or more existing slides to a new position in a deck (e.g. pull the agenda to slide 2, push an appendix to the end). The slides are identified by their slide OBJECT IDs and moved together as a contiguous block, preserving the relative order you list them in. ID flow: get presentationId from the deck URL, and get each slideId from get_presentation (outputFormat "map" gives a compact slideId index) or from the slideId/slideIds returned by create_slide or build_deck_from_outline — never use a slide number/position. Returns the full new slide order so you can verify the result without a follow-up read.
Replace image
Swap an existing image element on a slide for a new image URL, in place: the element keeps its exact size, position, and objectId — only the underlying picture changes. Use it to update what an existing image shows (refresh a logo, swap a product photo, update a screenshot); use Add image instead to create a new image at coordinates you specify, or Replace shapes with images to match shapes by placeholder text. CENTER_INSIDE fits the new image inside the original frame keeping aspect ratio (default); CENTER_CROP fills the frame and may crop. ID flow: pass the image's existing object ID in imageObjectId — get it from the id returned by add_image (or from get_presentation with outputFormat "map"/"json"); the same objectId is returned so you can chain further edits to that element.
Replace shapes with chart
Replaces every placeholder shape whose visible TEXT matches a token (e.g. '{{revenue_chart}}') with a chart pulled from a Google Sheet. Use it to fill template-driven decks where chart placeholders are typed into text boxes ahead of time; pairs with replace_text and replace_shapes_with_images to fully populate a templated slide. The token is matched against shape text, NOT shape object IDs or names, so no element IDs are needed here — only the presentationId, the source spreadsheetId, and the integer chartId. Choose LINKED (default) so the chart can later be refreshed with the latest Sheet data, or NOT_LINKED_IMAGE for a static snapshot. Returns occurrencesChanged (how many placeholders were filled). For LINKED charts the API does NOT return the new chart's objectId, so to refresh it later you must run get_presentation to find the SheetsChart element's objectId. If the token isn't in the deck yet, insert it first with replace_text.
Replace shapes with images
Replaces every placeholder shape in a presentation with an image, by matching the shape's TEXT content (e.g. {{company-logo}}) rather than its object ID. Use it to fill image placeholders across a deck in one batch call (e.g. after build_deck_from_outline / create_slide laid out branded templates with {{...}} tokens). Takes the presentationId plus a list of placeholder-text-to-image-URL mappings; it does NOT take slide or shape object IDs - targeting is purely by the literal text inside the shapes. Returns the count of shapes replaced (totalReplacements) and a per-placeholder breakdown (replacementDetails); a result of 0 means the placeholder text was not found verbatim in any shape.
Replace text
Find-and-replace text across a presentation in one batch — ideal for filling template placeholders (e.g. {{customer-name}}, {{date}}) with real values for mail-merge or generated decks. Pass each search/replace pair in textReplacements; optionally scope a replacement to specific slides via that pair's pageObjectIds (slide OBJECT IDs, not slide numbers). Returns occurrencesChanged per pair so you can confirm what was actually replaced. Requires the presentationId; if you also need slide object IDs, get them from get_presentation (outputFormat "map") or from create_slide / build_deck_from_outline.
Set element alt text
Set the accessibility alt text (title and/or description) on a single existing page element - an image, shape, table, line, group, chart, or video - so screen readers and accessibility/compliance checks (WCAG, Section 508) can describe it. Use this after creating or locating an element to make a deck accessible. Identify the element by its exact objectId: every create-element action returns the id it used (e.g. 'Add image' imageId, 'Add shape with text' shapeId, 'Add table' tableId), or look it up with 'Get presentation' (outputFormat 'map' or 'json'); never invent or guess an id. Provide a title and/or a description - passing an empty string ("") clears that field while omitting it leaves it unchanged; at least one is required. Alt text applies only to page ELEMENTS, never to slides/pages. Echoes back the objectId so you can chain further edits on the same element.
Set image outline and link
Sets the border (outline) and/or clickable link of an existing image on a slide, in place, without replacing the picture — use it to frame an image, recolor/restyle its border, or make it link to a URL. Outline controls: color (RGB 0-1), weight (thickness in points), dash style, and transparency; link controls: point the image at an http(s) URL or pass an empty string to remove the link. Only the properties you set are changed (the API field mask is built to match), so unset fields are left untouched. Identify the image by the exact object ID of an image element that already exists — get it from the response of the action that created it (e.g. 'Add image' returns the imageId) or from 'Get presentation'; never invent or guess the ID. Note: the Slides API does NOT allow setting image effects (brightness, contrast, transparency of the picture itself, recolor filters like grayscale/sepia, or cropping) — those are read-only. To swap the picture, use 'Replace image'; to move or resize it, use 'Update element transform'.
Set slide background
Set a single slide's background to a solid color, a stretched image, or inherit it from the slide's layout/master. Use when restyling one slide's backdrop (not a shape's fill — use 'Update shape properties' for that; use 'Add image' to place a movable picture). Choose backgroundType: SOLID_COLOR fills the slide with one RGB color (0-1 per channel) plus optional transparency; IMAGE stretches a public http(s) image to cover the slide; INHERIT_FROM_PARENT removes this slide's own background so it falls back to its layout/master. ID flow: pass the target slide's page object ID in slideId (NOT the slide number). Only the background changes; the field mask is built automatically and the update is atomic (on failure the slide is left unchanged). Returns the same slide object ID under both slideId and objectId so follow-up actions can chain off it.
Ungroup objects
Ungroup one or more grouped page elements ('elementGroup') back into their individual child elements; pass an array to ungroup many in one atomic batchUpdate. After ungrouping, each child (shape, text box, image, line, etc.) becomes an independent page element and keeps its existing child objectId, so you can then move, resize, restyle, or delete the pieces separately — for example to reposition just one element of a logo lockup. ID flow: the group objectIds you pass must be real existing group IDs — get them from get_presentation (outputFormat 'map' or 'json'), where groups appear as 'elementGroup' elements listing their child objectIds, or from the id returned by the group action that created them. Do NOT invent IDs. The group IDs cease to exist after the call; to address the now-independent children, re-read them via get_presentation (outputFormat 'map').
Update element transform
Move, resize, rotate, or shear an existing page element (shape, image, text box, line, group, etc.) on a slide by updating its transform matrix. Use it to reposition or scale elements after creating them or after reading the current layout. Requires the object ID of an element that already exists — get it from the action that created the element (every create action returns the id it used) or from get_presentation (outputFormat "map" or "json"). Never invent or guess the element ID.
Update element z-order
Reorder one or more page elements front-to-back (z-order / stacking order) on a single slide, choosing an operation: BRING_TO_FRONT, BRING_FORWARD, SEND_BACKWARD, or SEND_TO_BACK. Use it to fix overlap - e.g. put a label on top of an image, push a background shape behind text, or bring a highlighted box to the front. All listed elements move together in one atomic batch. This action consumes existing element object IDs: pass the exact objectId of each element (from the create action that returned it, or from get_presentation with outputFormat "map" or "json") - never invent IDs or pass a slide number. Every element must be on the SAME slide and must not be grouped; whole slides and layout-inherited placeholders cannot be reordered. If any ID is wrong the whole batch is rejected and nothing moves.
Update line properties
Restyle an EXISTING line, arrow, or connector by changing only the properties you set: color, thickness, dash pattern, arrowheads, or transparency (everything else is left untouched). Use it to edit a line you already added with 'Add line' or any line found in the deck. It does NOT create lines ('Add line') and does NOT move or re-route endpoints ('Update element transform'). ID flow: pass the presentationId from the deck URL plus the line's existing objectId — use the id returned by 'Add line', or look it up via 'Get presentation' (outputFormat "map" or "json"). Never invent or mistype an object ID. The action echoes the line's objectId (as both objectId and lineId) so you can chain further edits.
Update paragraph style
Formats existing paragraphs in a shape or text box (alignment, line spacing, indentation, space above/below, bullets/numbered lists, and text direction); use it to style copy after the text already exists. Requires two existing IDs: the presentationId from the deck URL and the elementId of the shape/text box. Get elementId from the id returned when the element was created (add_shape_with_text, build_deck_from_outline, etc.) or from get_presentation (outputFormat "map" or "json"); never invent or guess it.
Update shape properties
Restyle an existing shape's appearance — background fill color/transparency, outline color/weight/dash-style/transparency, and content alignment — in one batch update; use it to polish a shape created by 'Add shape with text' (or any existing shape). Targets an existing shape, so it consumes IDs but creates none: pass the presentationId and the shape's objectId. Supply at least one styling field; fields left blank are unchanged.
Update table
Edits an existing table in a Google Slides presentation in one call: choose ONE operation via the 'operation' field (insert/delete rows or columns, merge/unmerge cells, set cell background fill, set column widths or row heights, or style cell borders) and supply only the inputs that operation needs. Use it after a table already exists (added via 'Add table'). It is index-driven, not ID-driven beyond the table itself: pass the table's object ID plus zero-based row/column indices, never the cell text or a slide number. The presentation is left unchanged if any input is invalid. On success the table's object ID is echoed back so you can chain further edits without re-fetching.
Update text style
Formats existing text and/or inserts/replaces text in a shape, text box, or table cell — applying character styles (bold, italic, color, font, size, link, etc.), paragraph styles (alignment, spacing, indentation), and bullet/numbered list formatting. Use after a deck's text elements exist to style or rewrite their content. ID flow: this action consumes the existing element's object ID via objectId — it does not create or return a new element ID. Get objectId from the create action that made the element (add_shape_with_text, add_table, etc. return the id they used) or from get_presentation (outputFormat "map" or "json"); never invent or guess it.
Triggers
Actions
Triggers
Actions
Create custom object
Creates a new record in a HubSpot custom object. Use 'List custom object types' to find the objectType and 'Get custom object context' to discover available properties.
Create custom object association
Creates an association between a custom object record and another record (contact, company, deal, or another custom object). Use default association for simple linking, or specify an association type ID for labeled associations.
Create meeting
Creates a new meeting in HubSpot. Requires only a title for the meeting. If start time is omitted, the meeting starts at the current time, so set it explicitly when logging a past meeting or scheduling a future one.
Delete custom object
Deletes (archives) a custom object record. The record goes to HubSpot's recycling bin and can be restored within 90 days.
Delete custom object association
Removes an association between a custom object record and another record.
Draft marketing email
Drafts a new HubSpot Marketing Email. Requires a name for the email. Returns the drafted email's ID, name, subject, state, and creation timestamp.
Find custom object
Searches for records in a HubSpot custom object. Supports full-text search, filters, sorting, and property selection. Use 'Get custom object context' to discover filterable property names.
Find email
Search email engagement records by subject. Returns the most recent emails first, including subject, sender, recipients, direction, status, and body. Body text is returned but is not searchable.
Find meeting
Searches for meetings in HubSpot. Accepts an optional search query, filters (date range, outcome, owner), and sort order. Returns a list of meetings including titles, notes, descriptions, start/end times, outcomes, and owner IDs.
Get association
Gets associations between HubSpot records. Accepts one or more source record IDs (comma-separated) in a single call and returns the associated records grouped per source ID. When getting associations for several records of the same type, pass all their IDs comma-separated in one call instead of calling this action once per record. Takes exactly three inputs: fromObjectType (the source record type), toObjectType (the associated record type to retrieve), and fromObjectId (one or more comma-separated source record IDs).
Get association labels
Gets the available association types and labels between two object types. Use this to discover valid associationTypeId values before creating labeled associations. Works with both standard objects (contacts, companies, deals, tickets) and custom objects.
Get company context
Gets all required information on company properties, and the actual property values from a specific company.
Get current user context
Gets the current user's email, hubspot_owner_id, and other important info for later action calls.
Get custom object
Gets a custom object record by its ID. Use 'Get custom object context' first if you don't know the available property names.
Get custom object associations
Lists records associated with a custom object record. Returns linked contacts, companies, deals, or other objects of the specified target type.
Get custom object context
Gets the schema (property definitions, types, and valid options) for a custom object type. Optionally retrieves actual property values for a specific record. Also use this to discover available property names and their types for filtering, creating, or updating records. Prefer 'Get custom object' when you already know which properties to fetch.
Get deal context
Gets required information on deal properties, available stages, and the actual property values from a specific deal.
Get HubSpot owners
Retrieves all HubSpot owners/users with optional filtering by email. Returns owner IDs that can be used in hubspot_owner_id fields when creating or updating contacts, companies, deals, and notes.
Get marketing email
Gets the full details of a HubSpot Marketing Email including its content widget structure. Requires a marketing email ID (use 'List marketing emails' to find one). Returns the email's name, subject, state, full content object, sender details, and timestamps.
Get meeting
Retrieves a single HubSpot meeting by ID. Requires a meeting ID, obtainable from the Find meeting action. Returns the meeting title, description, internal notes, start/end times, location, outcome, owner, attendees, and external meeting URL.
Get ticket context
Retrieves ticket pipelines, stages, and available properties to help with ticket creation and updates.
List custom object types
Lists all custom object types defined in the HubSpot account, showing their IDs, names, labels, and associated objects. Use the returned objectTypeId (e.g., '2-12345') as the objectType parameter in other custom object actions.
List marketing emails
Lists HubSpot Marketing Emails — use this to discover available email templates and campaign drafts, or to find a specific one by name when you don't have the ID. Accepts an optional limit (1–500, default 50). Returns a list of emails with their IDs, names, subjects, publish state, campaign names, and timestamps.
Search marketing emails
Search HubSpot Marketing Emails by keyword and filters to find a specific email when you don't have its ID. Keyword does a case-insensitive match on the email name and subject (not the body). Supports sorting by creation or last-updated date and filtering by date range, published state, and email type. Returns matching emails with their ID, name, subject, state, campaign, and timestamps.
Update custom object
Updates properties of an existing custom object record. Use 'Get custom object context' to discover available property names.
Update marketing email
Updates a HubSpot Marketing Email's name, subject, or content. Requires a marketing email ID and at least one of: name, subject, or content — call 'Get marketing email' first to inspect the current content widget structure before passing updated content. Returns the updated email's ID, name, subject, state, and updated timestamp.
Triggers
Property changed
Triggers when a property on a HubSpot object (a standard object like a contact, company, deal, or ticket, or a custom object) changes. Watching a specific property fires once per value transition and returns the new value under a key named new_ followed by the property name (e.g. new_dealstage when watching dealstage). Leave the property name empty to fire on any update to the object instead.
Actions
Add comment
Adds a comment to an issue. Call the search_for_issues action to get the issue ID or key if the user just provides the issue name.
Create version
Creates a new release version in a Jira project (e.g., 'RELEASE - 1.1.0'). Use this as the first step in a release workflow: create the version, then bulk-update ticket fixVersions to it, then transition tickets to 'Released'. Requires Administer Projects permission.
Find components
Returns a paginated list of components for one or more projects. Use this to discover component IDs before creating or updating issues with components.
Get comments
Returns all comments for an issue. Call the search_for_issues action to get the issue ID or key if the user just provides the issue name.
Get custom field options
Returns allowed options for a given custom field. Optionally scope by project and issue type to reflect context-specific options.
Get fields
Returns all Jira fields with schema metadata. Use this to find field IDs (e.g., customfield_12345) and understand their types.
Get priorities
Returns all issue priorities (id and name). Use this to map human-friendly names to IDs.
Get recent projects
Returns a list of up to 20 projects recently viewed by the user that are still visible to the user.
Get versions
Lists all release versions for a Jira project. Use this to look up version IDs before creating issues, updating fixVersions on tickets, or building release workflows. Supports filtering by status (released, unreleased, archived).
List assets
Lists asset summaries from the connected Jira Assets workspace. Use Search assets to filter with AQL
Search assets
Searches Jira Assets objects with Assets Query Language (AQL). Use List assets to browse without a filter
Update asset
Updates selected asset attributes while preserving the current object's other attributes
Actions
Add comment
Adds a comment to an issue. Call the search_for_issues action to get the issue ID or key if the user just provides the issue name.
Create version
Creates a new release version in a Jira project (e.g., 'RELEASE - 1.1.0'). Use this as the first step in a release workflow: create the version, then bulk-update ticket fixVersions to it, then transition tickets to 'Released'. Requires Administer Projects permission.
Find components
Returns a paginated list of components for one or more projects. Use this to discover component IDs before creating or updating issues with components.
Get comments
Returns all comments for an issue. Call the search_for_issues action to get the issue ID or key if the user just provides the issue name.
Get custom field options
Returns allowed options for a given custom field, scoped to the create metadata of a project and issue type.
Get fields
Returns all Jira fields with schema metadata. Use this to find field IDs (e.g., customfield_12345) and understand their types.
Get priorities
Returns all issue priorities (id and name). Use this to map human-friendly names to IDs.
Get recent projects
Returns a list of up to 20 projects recently viewed by the user that are still visible to the user.
Get versions
Lists all release versions for a Jira project. Use this to look up version IDs before creating issues, updating fixVersions on tickets, or building release workflows. Supports filtering by status (released, unreleased, archived).
Actions
Create action
Creates a new action for an integration. Actions are executable functions that can be invoked by agents.
Create agent
Creates a new agent in the workspace with optional instructions, model, and capabilities. Requires ASSISTANT_API scope.
Create trigger
Creates a new trigger for an integration. Triggers poll for events and activate workflows.
Export usage
Exports workspace usage data for the given date range. Pick the dataset (agents, assistants, users, workflows, projects, or models) and a from/to range; returns the matching records inline. Requires USAGE_EXPORT_API scope.
Export workflow runs
Exports workflow run and node execution data for a date range as flattened rows, one per node execution. Returns rows inline by default; results over 50 rows are returned as an attached CSV (same pattern as Power BI query results). Enable Return as CSV to force a file for smaller exports. Requires an API key with the WORKFLOW_API scope and workflow owner, editor, or workspace admin access.
Get action
Retrieves a single integration action with its full details, including source code, input fields, and confirmation flag. Prefer this over get integration with includeDetails when you only need one action — large integrations can exceed context limits when every action's code is returned together.
Get agent
Retrieves an agent's prompt, model, capabilities, conversation starters, attachments, and actions. Set includeDetails for API-native field names, canvas, and knowledge folder IDs. There is no list-agents API; the agent UUID is in the agent's settings page URL. Requires ASSISTANT_API scope.
Get integration
Retrieves an integration's summary (name, auth type, action/trigger list) by default. Set includeDetails for auth configuration, action code/input fields, and trigger polling code. For a single action's code without loading every action, use get action.
Get knowledge file
Retrieves details of a specific file in a knowledge folder including its processing status and summary. Requires KNOWLEDGE_FOLDER_API scope.
Get meeting
Loads a meeting's title, owner, attendees, times, shared notes, and transcript. Pass meetingId from File added to folder, or paste the meeting UUID from the meeting page URL. Attendees come from the linked calendar event and do not include the owner; recordings without a calendar event return an empty attendee list. Requires a personal or workspace API key with Meetings Read API scope. The key can read meetings the key owner recorded or can access through sharing. Personal notes are never returned.
Invite users
Invites one or more users to the workspace by email. Already-existing members are silently skipped. Pending join requests are automatically approved. Requires USER_MANAGEMENT_API scope and admin API key.
List agents
Lists agents shared with the API key in the connected Langdock workspace. Returns summaries by default or full agent details when requested. Requires ASSISTANT_API scope.
List integrations
Lists integrations in the workspace. Returns id and name by default. Set includeDetails to get description, auth type, integration type, and action summaries. Action source code is only available from get integration.
List knowledge files
Lists all files in a knowledge folder including their processing status. Requires KNOWLEDGE_FOLDER_API scope.
List models
Lists all available models for use with the Agent API, including their regions and capabilities. Requires ASSISTANT_API scope.
List skills
Lists skills in the workspace with optional search. Returns a short summary by default. Set includeDetails to include instructions and attached integration IDs. Pages the API automatically up to the limit.
Read folder file
Reads the file, or the shared meeting notes and transcript, from a File added to folder trigger. Pass folderId and eventId from the trigger output. Requires a personal or workspace API key with Workflow API and Knowledge Folder API scopes for files, or Workflow API and Meetings Read API scopes for meetings. Personal meeting notes are never returned.
Search knowledge
Performs semantic search across all knowledge folders shared with the API key. Returns relevant document chunks ranked by similarity. Requires KNOWLEDGE_FOLDER_API scope.
Update agent
Updates an existing agent's configuration. Only provided fields are changed; omitted fields stay unchanged. Updates the draft only; a separate publish step (not exposed by this integration) is required to make the changes active. Requires ASSISTANT_API scope.
Update integration auth
Updates the authentication configuration of an integration. Warning: changing authType deletes all existing user connections.
Update knowledge file
Replaces an existing file in a knowledge folder with a new version. The old file is removed and the new file is processed and embedded. Requires KNOWLEDGE_FOLDER_API scope.
Upload attachment
Uploads a temporary file for use in agent conversations. The returned attachment ID can be referenced in chat messages. For permanent, searchable documents use upload file to knowledge folder instead. Requires KNOWLEDGE_FOLDER_API scope.
Upload knowledge file
Uploads a file to a knowledge folder for permanent storage and semantic search. The file is processed, embedded, and made searchable across the workspace. For temporary conversation-scoped files use upload attachment instead. Supported types: PDF, Word, text, markdown, HTML, PowerPoint. Requires KNOWLEDGE_FOLDER_API scope.
Triggers
File added to folder
Starts when a file or meeting is uploaded or moved into the selected Library folder. Existing contents and edits do not trigger. Connect a personal or workspace API key with Workflow API scope. Personal keys use their owner's folder access. Workspace keys can access folders shared with the key or everyone in the workspace. Use Read folder file for the file, or Get meeting with meetingId for owner, attendees, notes, and transcript.
Actions
Search docs
Search across the Docs knowledge base to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Docs, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages.
Triggers
Actions
Add attachment
Adds files to an existing Linear issue's Attachments list. Use Create issue, Update an issue, or Create comment to show a file in the issue description or a comment.
Create customer
Creates a customer in Linear, used with Linear Asks to represent the external person or company a request came from.
Create customer request
Attaches a customer request (a Linear Ask) to an issue, linking external feedback to the work that addresses it. Identify the customer by Linear ID or by an external ID.
Create or update project milestone
Creates a new milestone or updates an existing one. Pass milestoneId to update.
Get project details
Gets the full details of a specific Linear project, including teams, members, and lifecycle dates.
List customer requests
Lists customer requests (Linear Asks) and the issues they are linked to, optionally filtered to one customer. Useful for surfacing unresolved external requests.
List customers
Lists customers in Linear, optionally filtered by name. Useful for finding the customer to attach a request to.
List cycles
Lists Linear cycles (sprints), optionally filtered by team. By default only active/upcoming cycles are returned.
List labels
Lists Linear issue labels, optionally filtered by label name. This returns label metadata only; when the user asks for tickets or issues by label, use this first to find the exact label name, then call Search issues with that label name.
List projects
Lists projects in the Linear workspace. Optionally filter by team or include completed projects.
List project statuses
Lists the workspace project statuses (Backlog, Planned, Started, Completed, etc.). Use this to look up the status UUID required by Create or update project.
List workflow states
Lists the workflow states (Backlog, Todo, In Progress, Done, etc.) for a Linear team. Use this to look up the state UUID required by Update an issue.
Triggers
Assignee assigned
Triggers when an issue is assigned to someone, and again when it is reassigned to a different person. Optionally scope to a single team.
Actions
Triggers
Actions
Triggers
Actions
Triggers
Actions
Close opportunity as lost
Add-on action (Dynamics 365 Sales) — requires the Sales app on the connected Dataverse environment. Closes an opportunity as Lost via the LoseOpportunity operation, which sets the opportunity state to Lost and logs an opportunity-close activity.
Close opportunity as won
Add-on action (Dynamics 365 Sales) — requires the Sales app on the connected Dataverse environment. Closes an opportunity as Won via the WinOpportunity operation, which sets the opportunity state to Won and logs an opportunity-close activity.
Create record
Creates a new record in a Dataverse table and returns the created record including its generated primary key.
Delete record
Deletes a Dataverse record by GUID from a specified entity set. This permanently removes the record.
Describe table
Describes a single Dataverse table: its primary ID and name attributes plus its columns (logical name, type, required level). Use this to discover the exact column names before listing, creating, or updating records.
Disqualify lead
Add-on action (Dynamics 365 Sales) — requires the Sales app on the connected Dataverse environment. Disqualifies a lead by setting its state to Disqualified with a status reason such as Lost or No longer interested.
Get record
Gets a single Dataverse record by its GUID from a specified entity set, with optional column selection and related-record expansion.
List records
Lists records from a Dataverse table using OData query options. Supports column selection, filtering, and ordering. Results are paginated internally up to the requested limit.
List tables
Lists available Dataverse tables (entities) in the environment, returning each table's logical name, entity-set name, and display name.
Qualify lead
Add-on action (Dynamics 365 Sales) — requires the Sales app on the connected Dataverse environment. Qualifies a lead via the QualifyLead operation, optionally creating a linked account, contact, and opportunity, and returns references to the records created.
Recalculate opportunity
Add-on action (Dynamics 365 Sales) — requires the Sales app on the connected Dataverse environment. Recalculates the actual value of a won opportunity via the CalculateActualValueOpportunity operation. Use after editing opportunity products or revenue to refresh the rolled-up value.
Triggers
Actions
Add client secret
Generates a new client secret for a Microsoft Entra application registration with a specified display name and expiration. Plaintext secret is redacted by default unless explicitly requested.
Add redirect URI
Adds a redirect URI to a Microsoft Entra application registration across Web, SPA, or Public Client platforms.
Assign app role
Assigns an application permission (app role) to an Entra application or service principal for a target resource API (e.g., Microsoft Graph).
Create permission grant
Creates a new delegated OAuth permission grant (oauth2PermissionGrant) for a service principal.
Delete permission grant
Revokes and deletes an entire delegated OAuth permission grant (oauth2PermissionGrant) by its grant ID.
Get application
Retrieves detailed properties of a Microsoft Entra application registration, including redirect URIs, credentials with expiration dates, and resolved API permissions.
Get manager
Returns the direct manager of a user by their ID or user principal name. Returns the manager's full profile, or indicates no manager is set.
Get permission grant
Retrieves detailed properties of a specific delegated OAuth permission grant by its grant ID.
List app role assignments
Lists application permissions (app role assignments) granted to an Entra application or service principal, including resolved permission names and resource APIs.
List expiring credentials
Scans tenant application registrations for secrets and certificates that are expiring within a specified number of days or are already expired. Only credential metadata (key IDs, hints, expiration dates) is returned; plaintext secrets are never exposed.
List permission grants
Lists delegated OAuth permission grants (oauth2PermissionGrants) for an application or service principal.
Remove app role
Revokes an application permission (app role assignment) from an Entra application or service principal by assignment ID or role name.
Remove client secret
Deletes an existing client secret from a Microsoft Entra application registration by its key ID.
Remove redirect URI
Removes an existing redirect URI from a Microsoft Entra application registration.
Search applications
Searches and lists Microsoft Entra application registrations with overview counts of credentials, redirect URIs, and configured permissions.
Triggers
Actions
Execute GraphQL mutation
Executes one GraphQL mutation operation that can change Fabric data. Use Inspect GraphQL schema first to identify the available mutation.
Execute GraphQL query
Executes one GraphQL query operation. Use Inspect GraphQL schema first when the operation's fields, return type, filters, or selection shape are not already known; do not use this action for introspection.
Triggers
Actions
Append to page
Appends HTML content to the bottom of an existing OneNote page, leaving the existing content in place. Cannot insert content between existing elements.
List notebooks
Lists OneNote notebooks sorted by most recently modified, with optional filtering by name, shared inclusion, and role.
List sections
Lists sections across all notebooks or within a specific notebook, sorted by most recently modified.
Replace page content
Replaces the entire body of an existing OneNote page with the HTML you provide, and optionally its title. Permanently deletes the existing content. Refuses safely, making no changes, if the page contains images or embedded files it cannot recreate.
Triggers
Actions
Create task
Creates a new task in a Planner plan or as a private To Do task. For Planner tasks, provide planId or planTitle. For private To Do tasks, set isPrivate=true or provide todoListName.
List categories
Retrieve the category labels configured on a Planner plan (category1 through category25) so they can be used when listing, creating, or updating tasks.
List groups
Retrieve all Microsoft 365 groups that the user is a member of. These groups can contain Planner plans.
Actions
Create chat
Creates a 1:1 or group Microsoft Teams chat. A 1:1 returns the existing chat if one already exists. Does not send a message.
Find chats
Searches existing Microsoft Teams chats by topic or by another participant's name or email. Searching for the signed-in user adds Notes (48:notes) when no chat-type filter is set; the signed-in user is not matched as a participant.
Get channel message
Retrieves a single channel message by its exact ID, including full content, subject, mentions, and attachments. Use this when you have a specific message ID and need its full details. Use 'Get channel messages' to browse or list recent messages instead.
Get meeting transcript
Retrieves the transcript for a Microsoft Teams meeting using the join URL, meetingRecap URL, or conference ID. By default, returns transcript text in the transcripts array. Set 'Return as file' to true only when you need downloadable VTT file output.
List all teams
Lists teams the user can access: direct memberships, Microsoft 365 group-backed Teams, and associated Teams.
List online meetings
Lists all online meetings the user has organized. Returns join URLs that can be used to retrieve transcripts.
Search messages
Searches for chat & channel messages in Microsoft Teams that match the specified query.
Search users
Search for users in your organization by display name or email. Useful for finding specific people when multiple users have similar names.
Triggers
New meeting transcript
Triggers when a transcript becomes available for a recently ended Teams meeting.
New reaction in channel
Triggers when someone reacts to a channel message or a reply in its thread. Optionally filter to one reaction type (Unicode emoji like 👍, or a display name like Like). Requires ChannelMessage.Read.All on the connection (granted when a channel-message action such as Get channel messages is enabled).
New reaction in chat
Triggers when someone reacts to a message in a Teams chat (1:1 or group). Optionally filter to one reaction type (Unicode emoji like 👍, or a display name like Like). Requires Chat.ReadWrite on the connection (granted when a chat-message action such as Get chat messages is enabled).
Actions
Triggers
Actions
Post message
Posts to a community as an update, announcement, poll, or praise, replies to a thread, and can upload and attach a file directly.
Remove community member
Removes a user from a community. Removes the signed-in user if no user is given.
Actions
Add update to item
Posts a comment to an item's update thread. Requires an item ID and the comment text. Returns the created update's ID and body.
Create board
Creates a new board in a workspace. Requires a board name and workspace ID; optionally set visibility (public/private/share) and description. Returns the created board's ID, name, kind, and workspace info.
Create column
Creates a new column on a board. Requires a board ID, column title, and column type (e.g. text, number, status). Returns the created column's ID, title, type, and settings.
Create group
Creates a new group (section) on a board. Requires a board ID and group name; optionally set a color. Returns the created group's ID, title, color, and position.
Create subitem
Creates a new subitem nested under a parent item. Requires a parent item ID and a name for the subitem. Returns the created subitem's ID and name.
Create task
Creates a new item on a board with column values pre-filled. Requires a board ID, item name, and column values as JSON. Returns the created item's ID and name.
Get boards
Lists Monday.com boards the connected account can access, optionally filtered to a single workspace. Internal subitem boards are hidden by default. Requires no inputs (optionally accepts workspace ID, limit, and subitem-board toggle). Returns boards with their ID, name, workspace, item count, and board type.
Get board schema
Retrieves the full structure of a board. Requires a board ID. Returns the board's columns (ID, title, type, settings), groups (ID, title, color), item count, and workspace info.
Get items
Gets items from a Monday board. By default, fetches all items on the board. If not specified, get the limit for the board from the get_boards action output, use itemIds to look up specific items by ID across boards, or searchQuery to find items by exact name. Returns an array of items with their ID, name, column values, and file attachment metadata.
Get item updates
Retrieves the comment thread on a specific item. Requires an item ID. Returns a list of updates with author, text content, timestamp, and file attachment metadata on updates and replies.
Get users
Lists Monday.com users with optional filters. Requires no inputs by default; optionally filter by user IDs, emails, or name search. Returns each user's ID, name, email, title, and admin/guest status.
Get workspaces
Lists all workspaces the connected account has access to. Requires no inputs. Returns each workspace's ID, name, kind, and description.
Move item to board
Moves an item from its current board to a different board. Monday auto-maps columns with matching IDs between boards. Requires an item ID, target board ID, and target group ID. Returns the moved item's new board and group.
Move item to group
Moves an item to a different group within the same board. Requires an item ID and the destination group ID. Returns the moved item's ID and new group.
Update board
Updates a single attribute on a board. Requires a board ID, the attribute to change (name, description, or communication), and the new value. Returns the board ID and confirmation of the update.
Update column
Updates a column's title and/or description on a board (changes the column's schema, not item cell values; for cell updates, use Update item). Requires a board ID, column ID, and at least one of title or description. Returns the column's updated title, type, and description.
Update group
Updates a single attribute on a group. Requires a board ID, group ID, the attribute to change (title, color, or position), and the new value. Returns the group's updated ID, title, color, and position.
Triggers
Actions
Create comment
Adds a comment to a Notion page, block, or existing discussion thread. Provide pageId to comment on a page, blockId to comment on a specific block, or discussionId to reply in an existing thread. Content supports inline Markdown (bold, italic, code, links).
Create database
Creates a new Notion database as a child of a page, with a defined column schema. Requires a parent page ID and a properties schema defining the database columns — always construct this from what the user describes. Returns the created database's ID, URL, and metadata.
Create page
Creates a new Notion page as a child of an existing page or as an entry in a database. Requires a parent ID and parent type (page_id or database_id); title, properties, and content are optional. Returns the created page's ID, URL, and timestamps.
Find databases
Searches for Notion databases by title across the workspace. Requires a search query string. Returns a list of matching databases with their IDs, titles, and URLs.
Find pages
Searches for Notion pages by title across the workspace. Requires a search query string. Returns a list of matching pages with their IDs, titles, and URLs.
Get comments
Retrieves all comments on a Notion page or block. Returns comment content, authors, timestamps, and discussion thread IDs.
Get database details
Retrieves the schema and metadata of a specific Notion database. Requires a database ID. Returns the database's property definitions, title, and metadata.
Get page blocks
Retrieves the block structure of a Notion page or block, including block IDs, types, and text content. Requires a page or block ID. Returns a list of blocks with their types, content, and nested children up to the specified depth.
Get page content
Retrieves the full content of a Notion page or block, including all nested child blocks, and converts it to Markdown. Requires a page or block ID. Returns the page content as a Markdown string.
Get page details
Retrieves the metadata and properties of a specific Notion page. Requires a page ID or URL. Returns the page's properties, parent, icon, cover, and timestamps.
Get users
Lists all users in the Notion workspace, including their IDs, names, emails, and types (person or bot). Use this to find a specific person's user ID for filtering, assigning, or mentioning.
Query database
Fetches pages from a Notion database with optional filtering, sorting, and pagination. Requires a database ID; filters, sorts, and pagination parameters are optional. Returns a list of matching pages with their properties.
Search
Searches across the entire Notion workspace or within a specific database for pages and databases. Requires a search query; database ID, type filter, and property filters are optional. Returns a list of matching pages and databases with their IDs, titles, and URLs.
Update database
Updates a Notion database's title, description, icon, cover, or property schema. Requires a database ID and at least one field to update. Returns the updated database metadata.
Update page
Updates a Notion page's properties, icon, cover, or trash status. Also appends content to an existing page: omit blockId and provide blockText with blockType 'markdown' to append a full markdown document of any length, or use a specific blockType (paragraph, heading_1, etc.) for a single block. Provide blockId to update an existing block in place instead. Use this action whenever you need to add content to an existing page.
Actions
Create folder
Creates a new folder in OneDrive. Supports creating nested subfolders by providing a path with forward slashes.
Get folder by name
Retrieves a folder from OneDrive by its name or path. Supports nested paths like "Parent/Child/Grandchild".
Triggers
Actions
Get company by website URL
Find a company using its website URL. The response includes a company ID that you can use with other endpoints to get details like financials, shareholders, and representatives.
Get company contact information
Retrieve contact information for a company using its unique ID. The response includes details such as email address, phone number, VAT identification number.
Triggers
Actions
Apply proposed time
Updates the event to a proposed start and end time. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Check event room booking status
Checks the organizer event's current room responses without waiting or polling. Use this after 'Create events' or 'Update event' to verify whether resource room requests are confirmed, declined, or still pending. Legacy events whose rooms were added as required attendees cannot be identified as rooms; use 'Get event' to inspect their raw attendees. A shared or non-organizer event copy may not be authoritative.
Create events
Creates an Outlook calendar event with subject, time, attendees, rooms, and optional recurrence. Rooms are submitted as booking requests; use 'Check room booking status' later to verify whether Exchange accepted or declined them. 'Location' only controls the event's displayed location and does not book a room. When 'Online meeting' is set to true without specifying a provider, Microsoft Teams is automatically selected for business accounts. Newlines in the description are converted to HTML line breaks. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Delete event
Deletes a calendar event by its ID. For recurring events: pass the series master ID to delete all occurrences, or pass a single occurrence ID to delete only that instance. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Find meeting times
Finds available meeting times for yourself and additional participants. Checks free/busy schedules and suggests optimal time slots within the specified window.
Find rooms
Lists conference rooms and meeting spaces in the organization with details including capacity, building, floor, and equipment.
Get calendar settings
Retrieves calendar settings including timezone, working hours, and other configurations.
Get event
Retrieves a specific event by its ID, including attachment metadata (name, type, size) but not file content. Use Get event attachments to download attachment files. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Get event attachments
Downloads file attachments from a calendar event. Use after Get event when you need the actual files. Pass Attachment names to select which files to download; leave empty to download every file that fits the response size limit. Supports shared/delegated calendars via Shared calendar owner.
Get events for specific date
Retrieves all calendar events for a specific date. Times are automatically displayed in the user's configured timezone. Use this for events on a specific single date like 'what do I have on Friday?' or 'meetings on March 15th'.
Get person profile
Retrieves a person's directory profile by email address, including job title, department, office location, and contact details.
Get room availability
Checks whether a meeting room is free or busy during a specific time window, given its mailbox email address.
Get today's events
Retrieves all calendar events for today from your calendar or a shared calendar. Times are automatically displayed in the user's configured timezone. Use this for 'what's on my calendar today?' or 'do I have meetings today?' queries.
List calendar events
Searches and filters calendar events by date range, subject, organizer, or status. Supports shared calendars: pass a colleague's email address in the Calendar field to access their events directly (no need to call 'List calendars' first). Also accepts a calendar ID or calendar name. Use this for date ranges, filtering by subject/organizer/status, or when you need advanced query options. For single-date queries, prefer 'Get today's events' or 'Get events for specific date' for simpler responses.
List calendars
Retrieves accessible calendars including your own and shared calendars. Use this to discover calendar IDs or names when you need to target a specific non-default calendar. For shared calendars, you can pass a colleague's email directly to 'List calendar events' without calling this first.
List categories
Lists all available categories from the user's Outlook mailbox with their assigned colors. Use this to discover category names before assigning them to events.
List proposed times
Retrieves attendee proposed times for an event. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
List recurring event instances
Lists the occurrences and exceptions of a recurring Outlook event series within a required date-time window. Prefer this over a date-range listing whenever the user asks about a specific recurring meeting's occurrences, instances, or schedule, or whether any were moved or cancelled: Outlook matches the series exactly instead of relying on subject filtering. Accepts any event ID belonging to the series (an occurrence, exception, or the series master) and resolves the series master automatically.
Propose new time
Tentatively accepts an event invitation and proposes a different time to the organizer. Use this when you are an attendee and want to suggest rescheduling. Microsoft Graph requires sending a response for proposed times. If the user is the event organizer, use 'Update event' instead to change the time directly. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Respond to event
Accepts, declines, or tentatively accepts a calendar event invitation. Useful for RSVPing to meetings, declining meeting requests, or marking tentative attendance. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Search people
Searches for people by name in the organization directory and mailbox contacts. When no search term is provided, returns people ranked by interaction frequency. Returns name, email, job title, department, and company.
Update event
Updates an existing calendar event. Room changes submit asynchronous booking requests; use 'Check room booking status' later to verify whether Exchange accepted or declined them. 'Location' only controls the event's displayed location and does not book a room. Supports partial time updates: if only the start time or end time is provided, the other is automatically preserved from the current event. The timezone is required when updating any time field. Use this to directly change event details when the user is the organizer or has edit rights. If the user is an attendee wanting to suggest a different time, use 'Propose new time' instead. Supports shared/delegated calendars: pass a colleague's email in 'Shared calendar owner' to act on their calendar (they must have granted you edit rights); leave it empty for your own calendar.
Actions
Add category to email
Adds one or more categories (also known as labels or tags) to an email. Merges with any existing categories on the email (does not remove them). Category names must match entries in the user's Outlook category list - use 'List categories' to find valid names.
Create contact
Creates a new contact in your personal Outlook address book or a specific contact folder.
Create draft in shared mailbox
Creates an email draft in a shared mailbox (e.g., support@company.com) or another user's mailbox for later review and sending. The draft appears in the target mailbox's Drafts folder. Requires membership in the shared mailbox or delegated access to the user's mailbox.
Create folder
Creates a new mail folder. Creates a top-level folder by default, or a subfolder when a parent folder ID is provided.
Create folder in shared mailbox
Creates a new mail folder in a shared mailbox. Creates a top-level folder by default, or a subfolder when a parent folder ID is provided.
Draft reply to message
Creates a draft reply for review (does NOT send) — use when the user wants to draft, prepare, or save a reply for review before sending. Use the toggle to choose Reply (sender only) or Reply all (sender and all recipients); use 'send_reply' instead to send the reply immediately.
Draft reply to message in shared mailbox
Creates a draft reply in a shared mailbox for review (does NOT send) — the draft appears in the shared mailbox's Drafts folder. Use the toggle to choose Reply (sender only) or Reply all (sender and all recipients); use 'send_reply_from_shared_mailbox' instead to send the reply immediately.
Flag email
Flags an email in your mailbox for follow-up, marks a flag complete, or clears it. Optionally set start and due dates to add a reminder. Complements the flagged filter in Search own emails.
Flag email in shared mailbox
Flags an email in a shared mailbox for follow-up, marks a flag complete, or clears it. Optionally set start and due dates to add a reminder. Requires membership in the shared mailbox or delegated access.
Forward email from shared mailbox
Forwards an email from a shared mailbox (e.g., support@company.com) to one or more recipients with optional comment.
Get current user
Gets the display name and email address of the account connected to Outlook. Useful for finding out who 'I' am — for example to check whether a mailbox the user mentions is the connected account's own mailbox or someone else's. To look up other people, use 'search_people' instead.
Get email
Gets the full content of a single email by ID and downloads all attachments. Set 'sharedFolderOwner' to the mailbox email address to fetch from a shared mailbox you have access to.
Get person profile
Retrieves a person's directory profile by email address, including job title, department, office location, and contact details. Searches the organization directory — for personal Outlook contacts, use List contacts instead.
List categories
Lists all available email categories (also known as labels or tags) from the user's Outlook mailbox with their assigned colors.
List contact folders
Lists all personal contact folders (default Contacts and subfolders). Use this to retrieve the contact folder ID before listing or creating contacts inside a folder.
List contacts
Lists contacts from your personal Outlook address book or a specific contact folder. To find people in the organization directory, use Search people instead. If listing from a contact folder, first use 'List contact folders' to get the folder ID.
List drafts
Lists draft emails from your own Drafts folder (own mailbox only). Use 'list_drafts_in_shared_mailbox' to list drafts from a shared mailbox.
List drafts in shared mailbox
Lists draft emails from a shared mailbox's Drafts folder. Returns draft subjects, recipients, creation dates, and attachment status. Use for browsing drafts in a shared mailbox before updating or sending them.
List folders
Lists mail folders in the user's mailbox. Returns both well-known folders (inbox, drafts, sentitems, deleteditems, junkemail, outbox, archive, conversationhistory, scheduled, clutter) and custom folders. Use folder type filter to show only well-known or custom folders.
Mark email read status
Marks an email in your mailbox as read or unread. Complements the read/unread filter in Search own emails.
Mark email read status in shared mailbox
Marks an email in a shared mailbox as read or unread. Requires membership in the shared mailbox or delegated access.
Move email to folder
Moves an email or draft to a different folder — use to delete an email or draft by moving it to deleted items, archive an email, organize emails into folders, or unarchive. Accepts well-known names (inbox, drafts, sentitems, deleteditems, junkemail, outbox, archive, conversationhistory, scheduled, clutter) or folder IDs from 'list_folders'.
Remove category from email
Removes one or more categories (also known as labels or tags) from an email. Category names are matched case-insensitively. Categories not present on the email are silently ignored.
Search own emails
Searches your own mailbox (including subfolders) and returns matching emails — by default with full plain-text bodies (toggle off via 'includeDetails'). Use 'search_shared_email_folders' for shared mailboxes, or 'get_email' when you already have a message ID and need attachments downloaded. If the user asks about the mailbox or inbox of a specific person, team, or email address, call 'get_current_user' first to check whether that mailbox is the connected account's own — if it is not, use 'search_shared_email_folders' instead.
Search people
Searches for people by name in the organization directory and mailbox contacts. When no search term is provided, returns people ranked by interaction frequency. Returns name, email, job title, department, and company.
Search personal contacts
Searches your personal Outlook Contacts folder by email address or display name. Results come only from personal contacts, not the organization directory or mailbox people.
Search shared email folders
Searches emails in a shared mailbox or another person's mailbox you have access to. Requires the mailbox's email address: if you only have a person's name, resolve it first (e.g. via 'search_people') or ask the user — never guess or invent an address.
Send draft from shared mailbox
Sends an existing draft email from a shared mailbox by ID. The draft must already exist in the target mailbox's Drafts folder.
Send email from shared mailbox or other user
Use when sending email from a shared mailbox (e.g., support@company.com) or on behalf of another user with delegated access. Requires 'Send As' or 'Send on Behalf' permission for user mailboxes, or membership in the shared mailbox.
Send reply
Sends a reply to an existing email immediately — use when the user wants to reply now, send a reply, or respond to an email. Use the toggle to choose Reply (sender only) or Reply all (sender and all recipients); use 'draft_reply_to_message' to create a draft for review instead of sending immediately.
Send reply from shared mailbox
Sends a reply to an email in a shared mailbox immediately — use when the user wants to reply now from a shared mailbox (e.g., support@company.com). Use the toggle to choose Reply (sender only) or Reply all (sender and all recipients); use 'draft_reply_to_message_in_shared_mailbox' to create a draft for review instead of sending immediately.
Update contact
Updates selected fields on an existing personal Outlook contact. Unspecified fields remain unchanged. Empty optional values are ignored and cannot clear a field. For a department-only change, set department and leave givenName, surname, displayName, and every other optional field unset. Clearing fields is not supported.
Triggers
Label changed on email
Triggers when categories are added to or removed from an email in your Outlook mailbox.
Label changed on email in shared inbox
Triggers when categories are added to or removed from an email in a shared inbox (an owner you have Mail.Read.Shared access to).
New email in shared inbox
Triggers when new emails are received in specified shared inboxes (users you have Mail.Read.Shared access to).
New email in shared mailbox folder
Triggers when emails appear in a specific folder of a shared mailbox (either newly received or moved to it). Requires Mail.Read.Shared permission and folder access.
Actions
Create compensation
Creates a compensation for an employee (one-time, recurring, fixed, or hourly). Bonuses not supported.
Create compensation type
Creates a new compensation type that can be used when creating compensations.
Get absence period
Retrieves an absence period by ID. Get absence period IDs from list_absence_periods or create_absence responses.
Get org unit
Retrieves an organizational unit (team or department) by ID. Get org unit IDs from list_employments or get_employment responses.
Triggers
Actions
Archive project
Archives a project, removing it from the active list while keeping its data. Archived projects can be restored in Pipedrive; this does not permanently delete the project.
Convert lead to deal
Converts a lead into a deal, optionally placing it in a specific pipeline and stage, and returns the new deal once the conversion completes.
Create activity
Creates an activity (call, meeting, task, and similar) optionally linked to a deal, person, or organization.
Create deal
Creates a new deal in Pipedrive with an optional value, associated contact, organization, pipeline, and stage.
Create lead
Creates a lead linked to a person or organization, optionally with a value and expected close date.
Create person
Creates a new contact person with optional emails, phone numbers, and organization link.
Create project
Creates a project on a board and phase. Requires a title, a board, and a phase; optionally sets a description, owner, start and end dates, and links to deals, persons, and organizations.
Create project task
Creates a task in a project. Requires a project and a title; optionally sets a description, an assignee, and a due date.
Find deal
Searches deals by a free-text term, optionally restricted to specific fields, exact-matched, scoped by status, person, or organization, and post-filtered by value range.
Find lead
Finds and filters leads by a title term, linked person, organization or owner, value range, currency, labels, expected-close window, a custom-field match, or a saved filter. Sortable by date added or updated.
Find organization
Searches organizations by a free-text term, optionally restricted to specific fields (name, address, notes, custom fields) and exact-matched.
Get current user
Gets the profile of the currently connected Pipedrive user, including name, email, company, and timezone.
Get deal
Gets the full details of a single deal by its ID, with custom fields resolved to their labels.
Get deal context
Gets a deal together with its attached products and activities, for a full picture of the deal in one call.
Get lead conversion status
Checks the status of a lead-to-deal conversion and returns the resulting deal ID once it has completed.
Get organization
Gets the full details of a single organization by ID, with custom fields resolved to their labels.
Get person
Gets the full details of a single contact person by ID, with custom fields resolved to their labels.
Get project
Gets a single project by ID, including its board, phase, status, dates, description, owner, and linked deals, persons, and organizations.
Get stage
Gets a single deal stage by its ID, including its name, pipeline, order, and win probability.
List activities
Lists activities, optionally filtered by completion status, type, owner, or a linked deal, person, or organization.
List deal products
Lists the product line items attached to a deal, with each item's price, quantity, discount, and total.
List deals
Lists deals with deep filtering: status, pipeline, stage, owner, linked person or organization, value and probability ranges, currency, expected-close and won-date windows, labels, a custom-field match, or a saved filter. Sortable by date added or updated.
List filters
Lists the saved filters defined in Pipedrive for a given object type, returning each filter's name and ID. Use it to discover a filter to pass to the 'filter' input on List deals, List organizations, Find lead, or List activities.
List organizations
Lists organizations with filtering by owner, labels, a custom-field match, an updated-date window, or a saved filter. Sortable by date added or updated.
List project activities
Lists the activities logged against a project, such as calls, meetings, and tasks recorded on its timeline.
List project boards
Lists the project boards in the account. Use it to find the board ID needed when creating a project.
List project phases
Lists the phases of a project board. Use it to find the phase ID needed when creating a project. Provide a board to scope the phases to that board.
List projects
Lists active projects, optionally filtered by status or phase. Returns each project's board, phase, status, dates, and linked deals, persons, and organizations.
List project tasks
Lists the tasks of a project, including each task's title, assignee, due date, and completion state.
List project templates
Lists the project templates in the account, which predefine boards, phases, and tasks for new projects.
List stages
Lists deal stages with their names, IDs, and pipeline, optionally scoped to a single pipeline.
Search leads
Searches leads by a term matched against their title, notes, and custom fields, optionally filtered by linked person or organization.
Search projects
Searches projects by a text term across their title and description, returning the closest matches ranked by relevance.
Search users
Finds Pipedrive users (colleagues) by name or email, returning each user's ID, name, email, and active status. Use it to look up a colleague's user ID for owner fields on other actions. Leave the term empty to list all users.
Update activity
Updates an existing activity, including marking it done, rescheduling it, or changing its links.
Update deal
Updates an existing deal, changing any of its value, stage, status, owner, or custom fields.
Update deal product
Updates a product line item on a deal, such as its price, quantity, discount, or comment.
Update person
Updates an existing contact person's name, emails, phone numbers, organization, or custom fields.
Triggers
Changed activity
Triggers when an activity is created or updated. You can additionally filter any event to records where a specific field matches given value(s).
Changed deal
Triggers when a deal is created or updated. You can additionally filter any event to records where a specific field matches given value(s) (e.g. Updated with status = won to react to deals becoming won).
Changed lead
Triggers when a lead is created or updated. You can additionally filter any event to records where a specific field matches given value(s).
Changed note
Triggers when a note is created or updated. You can additionally filter any event to records where a specific field matches given value(s).
Actions
Execute query
Run DAX queries, DMVs, MDX queries, or INFO DAX functions against a Power BI dataset. Results with more than 50 rows are returned as a CSV file to preserve full data for analysis. DAX queries on standard datasets use the Execute Queries API. Live connection/Azure Analysis Services datasets, DMVs, MDX queries, and INFO DAX functions use XMLA endpoint.
Export paginated report (initiate)
Initiates a Power BI paginated report export job. Supports more formats than regular reports including XLSX, CSV, DOCX, XML. Returns export ID for use with fetch action.
Export report to file (fetch)
Fetches a Power BI report export (regular or paginated) by checking status and downloading the file if ready.
Export report to file (initiate)
Initiates a Power BI report export job. Returns export ID for use with fetch action.
Get dataset schema
Gets table and column metadata from a Power BI dataset using the XMLA endpoint. Call this for tables, columns, schema, or table structure. It does not return measures or relationships. The complete catalog is always attached as a JSON file; inline lists are a preview of the first 3 items (and the first 3 columns per table). When the user wants a full semantic model, to describe a dataset including measures and joins, or to ground DAX, also call Get semantic model measures and Get semantic model relationships. Dataset accepts a name, URL, or ID; search_datasets if the name is ambiguous. Requires Premium Per User (PPU), Premium capacity, or Fabric capacity with XMLA endpoint enabled.
Get semantic model measures
Gets measures (name, table, and DAX expression when permitted) from a Power BI semantic model using the XMLA endpoint. Call this whenever the user asks for measures, DAX measures, or KPIs; Get dataset schema does not include them. The complete catalog is always attached as a JSON file; the inline list is a preview of the first 3 items. When the user wants a full semantic model, to describe a dataset including measures and joins, or to ground DAX, also call Get dataset schema and Get semantic model relationships. Dataset accepts a name, URL, or ID; search_datasets if the name is ambiguous. Requires Premium Per User (PPU), Premium capacity, or Fabric capacity with XMLA endpoint enabled.
Get semantic model relationships
Gets relationships with from/to table and column names from a Power BI semantic model using the XMLA endpoint. Call this whenever the user asks how tables join or relate; Get dataset schema does not include relationships. The complete catalog is always attached as a JSON file; the inline list is a preview of the first 3 items. When the user wants a full semantic model, to describe a dataset including measures and joins, or to ground DAX, also call Get dataset schema and Get semantic model measures. Dataset accepts a name, URL, or ID; search_datasets if the name is ambiguous. Requires Premium Per User (PPU), Premium capacity, or Fabric capacity with XMLA endpoint enabled.
Actions
Create KB article
Create a new knowledge base article. IMPORTANT: The contentHtml field is mapped to body_html in the API.
List custom fields
Get all custom fields configured in Pylon. REQUIRED: objectType must be one of: account, issue, or contact.
Search accounts
Search for accounts using field-specific operators. IMPORTANT: Each field has specific allowed operators - domains/tags: contains, does_not_contain, in, not_in | name/external_ids: equals, in, not_in. Use filterValue for single values (equals, contains, does_not_contain), filterValues for arrays (in, not_in).
Triggers
Actions
Create content note
Creates an Enhanced Note (ContentNote) and optionally links it to one or more records via ContentDocumentLink.
Create contract
Creates a new Salesforce Contract. Status must be a Draft-category status (e.g. 'Draft' or 'In Approval') — Salesforce rejects creation with Status='Activated'. Activate via update_contract after creation.
Find account
Searches accounts by name or keyword (full-text search). For filtering by owner, industry, or any field, or to list all accounts, use Execute SOQL query instead.
Find contract
Finds contracts. Two modes: (1) text search on indexed Contract fields when 'Search Term' is provided (>=2 chars, no wildcards alone); (2) filter-only query when 'Where' is provided without a search term (use this for AccountId, Status, or date filters). At least one of the two must be set.
Find opportunity
Searches opportunities by name or keyword (full-text search). For filtering by owner, stage, close date, or any field, or to list all opportunities, use Execute SOQL query instead.
Find records (advanced)
Executes advanced querys on supported Salesforce objects based on SOQL queries.
Get account context
Gets all fields and metadata for the Account object, plus the org's Account record types with their IDs, whether each one creates a Person Account (isPersonType) and whether the connected user may use it (available). Use this to find the record type ID needed to create a Person Account, since those IDs differ per org.
Get content note
Gets an Enhanced Note (ContentNote) and optionally its ContentDocumentLink associations.
Get content notes for record
Retrieves Enhanced Notes (ContentNote) linked to a record via ContentDocumentLink.
Get custom object context
Retrieves the field schema for a Salesforce custom object, showing available fields, their types, and requirements.
List custom object records
Lists records from a Salesforce custom object. Use this to browse records without a search term.
List custom object types
Lists all custom objects available in the Salesforce org, showing their API names and labels.
Triggers
Actions
Create incident
Creates a new ServiceNow incident. Note: ServiceNow instances may have custom mandatory fields beyond short_description. If creation fails due to missing required fields, use get_incident_metadata with onlyRequired=true to discover instance-specific mandatory fields, then provide them via the additionalFields parameter.
Find knowledge articles
Searches the ServiceNow knowledge base for information. Use this whenever the user asks about information that could be documented in the ServiceNow knowledge base. Returns article titles, numbers, states, categories, and knowledge base names. Use get_knowledge_article to then retrieve the full article body.
Get current user
Gets the name, email, and ID of the person connected to ServiceNow. Useful for finding out who "I" am, for example before assigning something to yourself. To look up someone else, use Find users instead.
Get incident metadata
Gets field definitions for the incident table, including labels, data types, required flags, and allowed values for choice fields. Use this action to discover which fields are mandatory in your ServiceNow instance before creating or updating incidents. Set onlyRequired=true to get only mandatory fields. Custom fields and their requirements vary by instance.
Get knowledge article
Retrieves the full content of a specific knowledge article by sys_id. Returns the complete article body (HTML in the 'text' field), metadata, and optionally attachments. Use find_knowledge_articles first to search and get the sys_id.
Triggers
Actions
Add section to page
Append one or more sections to the bottom of an existing SharePoint page; use it to add a section, table, text block, or web part to a page that already exists. Reads the page first and refuses, making no changes, if it contains web parts the SharePoint Pages API cannot recreate (News, Lists, Hero, Highlighted Content, Document library, custom or third-party web parts).
Create folder
Creates a folder in a SharePoint drive. Supports nested folder paths (e.g., 'folder1/folder2/folder3').
Create page
Create a new SharePoint page with text, multi-column sections, images, dividers, spacers, buttons, YouTube embeds, and an optional right-rail side rail.
Find site users
Finds a person in a SharePoint site and looks up their site user ID. Requires the site ID and the person's email address or exact display name, and only finds people who already have access to that site. Returns the person's site user ID (the LookupId) with their display name, email address and login name; this ID is what a Person or Group column expects when it is set with create_list_item or update_list_item.
Get file
Gets / downloads a file from Sharepoint based on the item ID and attaches it to the chat, use this action to get the contents of a file.
Get page
Read a SharePoint page and return its content, metadata, and layout. Only works with modern SharePoint pages.
Get sensitivity label
Get the sensitivity label(s) applied to a file and its protection state. Returns label IDs, assignment method, and whether the file is encrypted (Purview/Azure RMS) and so can't be read.
List drive children
Lists files and folders at a single level in a SharePoint drive or folder. Returns both files and subfolders for navigating the drive hierarchy. Accepts a drive ID or a SharePoint folder/drive URL.
List files in SharePoint folder
Lists files and subfolders in a SharePoint folder. Always returns direct child folders alongside files for nested folder navigation. Enable includeSubfolders to recursively list all files within subfolders.
Replace page content
Replace the entire content of an existing SharePoint page. Permanently deletes all existing content and replaces it with what you provide. Refuses safely if the page contains web parts the write API cannot recreate.
Resolve SharePoint URL
Turns a pasted SharePoint URL into the Graph IDs needed by other SharePoint actions. Works for sites, lists, list items, files, folders, and pages. Returns the resource kind and IDs such as siteId, listId, itemId, driveId, driveItemId, and pageId. For files and pages, also returns an attachable items payload. To attach a file from a pasted link in chat, use Create attachment from URL. For looking up a modern Site Page by name, use Resolve page.
Actions
Add discount codes in bulk
Adds many redeem codes to an existing discount, so each customer can get a unique code for the same offer. Create the discount first, then add up to 250 codes per call.
Add product media from URL
Adds an image, video, or 3D model to a product from a publicly reachable HTTPS URL. Shopify downloads the file itself, so the URL must not require a login.
Add products to collection
Adds products to a collection that keeps a manual list of products. Collections whose membership is defined by rules or that mix several product sources are refused, because their membership is not editable this way.
Adjust inventory
Adds or removes stock for one inventory item at one location by a relative amount, and records a reason for the store's inventory history. Use Check inventory levels first to read the IDs and current quantity.
Check inventory levels
Checks stock per location for the store's inventory items, including available, on-hand, committed, and incoming quantities. Returns inventory item and location IDs (location names are omitted so this works without the read_locations scope). Use the returned inventoryItemId with Adjust inventory.
Create discount code
Creates a percentage or fixed-amount discount code that customers enter at checkout, optionally limited to certain products or collections, a date range, or a usage cap. Shopify allows only one cart minimum: set either minimumSubtotal or minimumQuantity, never both — leave the other empty.
Find collections
Finds collections and reports which ones accept manual product changes. Use it to get the collection IDs needed to add or remove products.
Find discount codes
Finds code-based discounts with their codes, status, usage, and validity window. Automatic discounts are not included because they have no code to hand to a customer.
Find orders
Finds recent orders by keyword, payment status, or fulfillment status, and returns each order's Shopify Order ID, name (for example #1001), totals, and status. Customer email/phone/name are not returned (Protected customer data). Use the returned id with Get order or Fulfill order. Shopify only exposes an app's recent orders (roughly the last 60 days).
Find products
Finds products by keyword, vendor, product type, tag, or status, and returns their IDs, prices, and stock totals. Use it to locate the product IDs that the other product actions need.
Fulfill order
Marks an order's remaining items as fulfilled and optionally records tracking details and notifies the customer. Requires a Shopify Order ID from Find orders (not the order name/number).
Get order
Gets one order by its Shopify Order ID (line items, totals, discounts, addresses at city/country level, fulfillments). Customer email, phone, name, and street address are omitted without Protected customer data approval. The Order ID is not the order name or number (#1001) — run Find orders first and pass the returned id.
Get product
Gets one product with its description, variants, prices, stock, media, and collection memberships. Use it before updating a product so the current values and variant IDs are known.
Get shop details
Gets the store's name, contact details, domains, currency, timezone, and plan. Use it to confirm which store a connection points at, or to read the store's currency before writing prices.
Remove product media
Removes media from a product while keeping the file in the store's file library, so the same file can be reused on other products.
Remove products from collection
Removes products from a collection that keeps a manual list of products. The products themselves are untouched, only their membership in the collection changes.
Reorder product media
Reorders a product's media, which decides the order shoppers see and which image is the featured one. Media that is not listed keeps its relative order after the listed media.
Update product
Updates a product's title, description, handle, status, type, vendor, tags, or SEO fields. Only the fields provided are changed, and tags replace the product's whole tag list.
Update product media
Updates the alt text or file name of a piece of product media. Use Get product to read the media IDs first.
Triggers
Actions
Download file
Downloads a file shared in Slack, such as an image, PDF, or document. Use the file ID from the files array returned by Get conversation history, Get thread replies, or Search messages. The connected account must have access to the file's channel. Files larger than 100 MB are not downloaded.
Get channels by name
Searches for channels in your Slack workspace by name (public and private team channels only).
Get conversation history
Fetches a conversation's history of messages and events. Returns message metadata including thread reply counts. To fetch the actual thread replies for specific messages, use the 'Get thread replies' action with the thread_ts_unix value. The showThreads option attempts to fetch all thread replies inline but may be incomplete for channels with many threads. All timestamps are in UTC.
Get people
Lists Slack users in the workspace. Paginates through the full user list. By default each user includes id, real_name, profile.email, and profile.image_512. Only set includeFields when the user explicitly names additional fields to include in the response.
Get thread replies
Retrieves all replies in a specific Slack thread. Use this to fetch thread content reliably. Get the channelId and threadTs from 'Get conversation history' or 'Search messages' results (use the thread_ts_unix field).
List user conversations
Lists all conversations (channels, DMs, group DMs) that a specific user is a member of.
Triggers
New message by search
Triggers when a new message is found by searching for a specific keyword or other criteria.
New message in channel
Triggers when a new message was posted in a channel (public, private, DM, etc.).
Actions
Ask Cortex Analyst
Asks Snowflake Cortex Analyst a natural-language question against a semantic view, then runs the generated SQL.
Describe semantic view
Describes the metrics, dimensions, facts, and relationships on a Snowflake semantic view.
List Cortex Search services
Lists Cortex Search services the current role can see. Use the qualifiedName with Query Cortex Search service (REST).
List semantic views
Lists Snowflake semantic views the current role can see. Use before describing or querying a semantic view.
Preview Cortex Search (SQL)
Runs Snowflake's SEARCH_PREVIEW SQL debug function against a Cortex Search service. Prefer Query Cortex Search service (REST) for the production REST API.
Query Cortex Search service (REST)
Searches a Cortex Search service through the production REST API. Use this instead of Preview Cortex Search (SQL), which only runs Snowflake's SEARCH_PREVIEW debug function. Prefer a fully qualified name from List Cortex Search services.
Triggers
Actions
Get consumer insights
Retrieves Statista Consumer Insights survey data as a crosstable for a specific question or answer, optionally scoped to a country and survey year. Designed to work with results from the 'search_consumer_insights' tool - pass a question ID (or answer ID) from a search result. Always cite the source of the data in your response.
Get market insights indicator
Retrieves the data for a specific Statista Market Insights indicator using its unique identifier, optionally scoped to up to five geographies. Designed to work with results from the 'search_market_insights' tool - pass an indicator ID and, optionally, geo codes from that indicator's covered geographies. Always cite the source of the data in your response.
Get statistics data by ID
Retrieves detailed statistical information for a specific Statista chart or dataset using its unique identifier, including full numerical values, source details, and metadata. Works with results from the 'search_statistics' tool - pass an ID from a search result to dive deeper. Always cite the source of the data in your response.
Search consumer insights
Searches Statista Consumer Insights for survey questions on consumer behaviour, preferences, demographics and brand perception. Returns matching survey questions with their question IDs and answer options. Pass a question ID (or answer ID) to the 'get_consumer_insights' tool to retrieve the survey data. Use this for what people do, buy, prefer or think; use 'search_market_insights' for market size, revenue or volume, and 'search_statistics' for published charts.
Search market insights
Searches Statista Market Insights for market indicators - market size, revenue, volume, growth forecasts and related KPIs across industries and regions. Returns matching indicators with their identifiers and the geographies each one covers. Pass an indicator ID (and a covered geo code) to the 'get_market_insights_indicator' tool to retrieve its data.
Triggers
Actions
Create customer
Creates a new customer in Stripe. Use the Email and Name fields for basic info, and Custom Parameters for all other Stripe customer fields.
Get customer funding instructions
Retrieves bank transfer funding instructions for a customer's cash balance in a specific currency.
Triggers
Actions
Get view by path
Gets views with a given viewUrlName. viewUrlName is not site-wide unique, so check count/isAmbiguous and use workbook or project context when multiple views are returned.
Get view image
Returns a PNG snapshot of a Tableau view as an image attachment. Use this to show a chart or dashboard inline.
Get workbook preview image
Returns the thumbnail preview image (PNG) of a workbook as a file attachment. Useful for 'show me what's in this workbook'.
List custom views
Gets all custom views on the site. Leave filters empty unless Tableau accepts the exact filter syntax.
List projects
Lists projects (folders) in the Tableau site, optionally filtered by project name or parent project.
List workbooks
Lists workbooks in the Tableau site, optionally filtered by project (folder) name or workbook title.
Query data source
Queries a published data source directly, bypassing view-level filters. Requires Tableau Cloud or Tableau Server 2025.1+.
Query view data
Extracts data from a specific standard (non-custom) Tableau view in CSV format. Use get_custom_view_data for custom views. Multi-measure views return Tableau's tall format with Measure Names and Measure Values columns.
Triggers
Actions
Get audit logs
Lists audit log entries from UiPath Orchestrator showing who performed which action on which component and when. Use for security reviews and change tracking, e.g. who started a job or changed a queue.
Get folders
Lists folders you can access in UiPath Orchestrator (including Shared, personal workspaces, and Solution folders) and returns their IDs. Use this to discover the folder ID required by other actions — processes published from Studio Web often live under a personal workspace or Solution folder, not Shared.
Get job details
Retrieves full details of a UiPath job for deep troubleshooting, including expanded robot, process release and machine info, input/output arguments, error details, and (by default) the job's execution logs. Use this to investigate why a job behaved a certain way; for a quick status check use check_job_status instead.
Get jobs
Lists jobs in UiPath Orchestrator, optionally filtered by state, process name, and folder. Use to see what's running, find recent failures, or look up a job ID.
Get job statistics
Computes success and failure statistics per automation process over a time window, from UiPath Orchestrator job history. Use to report on automation reliability, e.g. how many jobs succeeded vs failed for a process this month. Each process also lists faultedJobIds (Ids of its Faulted jobs) you can pass to Get job details for root-cause analysis.
Get processes
Lists automation processes (releases) in UiPath Orchestrator, optionally filtered by name and folder. Leave folder ID empty to list processes across accessible folders; scoping to Shared will miss processes published into a personal workspace or Solution folder.
Get queue items
Lists work items from UiPath Orchestrator queues, optionally filtered by queue, status, or business reference. Use to inspect transaction items, find failed items, or look up an item by reference. Each item surfaces its failure reason (processing exception type and review status); enable Include details to also return its specific content, output, analytics, and full processing-exception details.
Actions
Get automation idea
Retrieves the full details of one Automation Hub idea by ID, optionally with its documents, components, and collaborators.
List applications
Lists the Automation Hub application inventory (systems such as SAP or Salesforce) to look up the application ID that filters Search automation ideas. It returns the systems themselves, not the automations that use them; use Search automation ideas to find automations.
List categories
Lists the Automation Hub category hierarchy with the category IDs used to filter Search automation ideas.
Triggers
New automation idea
Triggers when a new automation idea is created or submitted in Automation Hub. Event data includes newPhase / newStatus (initial pipeline values). Optionally filter by phase, status, category, or application.
Updated automation idea
Triggers when an automation idea is updated (phase/status moves or other edits). Does not fire on create. Event data includes newPhase / newStatus (current values after the update); oldPhase / oldStatus are null because the Open API does not expose prior values. To watch ideas going Live, set Phase ID to your tenant's Live phase ID from a Search automation ideas card.
Actions
List indexes
Lists the vector indexes in a project and region, including each index's ID and whether it accepts stream updates. Use it to find the index ID needed to upsert datapoints.
List projects
Lists the Google Cloud projects the connection can access, with their IDs and numbers. Use it to find the project id / number the other actions need.
Triggers
Actions
Create folder
Creates a new folder or project under a parent folder. Use isProject=true to create a project with status tracking.
Delete task
Moves a task to the Recycle Bin. The task can be restored later using the update_task action with restore=true.
Get task
Returns detailed information about a task including its description, status, dates, and assignees.
Get timelogs
Retrieves time tracking entries. Filter by task, folder, user, or date range. Returns total hours worked.
Update account metadata
Update account metadata (key-value pairs). Note: This updates metadata only, not subscription settings. Requires admin privileges.
Update comment
Edit the text of an existing comment. Note: Wrike only allows editing within 5 minutes of creation. Use get_task_comments first to obtain the commentId.
Actions
Create organization
Creates a Zendesk organization with a name and optional details, like notes, domains, tags, group, or custom fields.
Get ticket conversation log
Gets a specific ticket by ID along with its complete conversation history and logs.
List users
Retrieves a list of users from Zendesk, with optional filtering by role, permission set, or external ID.
Search
Searches across Zendesk for tickets, users, organizations, and groups using Zendesk's query syntax.
Triggers
Fragen & Antworten
Integrationen verbinden Langdock mit deinen bestehenden Tools, sodass Agents und Workflows interne Dokumente durchsuchen, Aktionen auslösen, Daten aktualisieren oder Abläufe in deinen Apps automatisieren können.
Langdock unterstützt eine große Bandbreite gängier Business‑Tools wie Google Drive, Notion, Confluence, Slack, Salesforce, Jira, Asana und viele mehr. Du kannst zudem individuelle Integrationen für jedes Tool erstellen, das eine API anbietet.
Das ist nicht notwendig. Die meisten Verbindungen funktionieren sofort nach der Aktivierung. Wenn du jedoch erweiterte Funktionen oder Actions benötigst, bietet Langdock einen integrierten Builder an. Damit erstellst du deine eigene Logik – inklusive unterstütztem JavaScript-Flow.
Absolut. Langdock nutzt eine sichere Authentifizierung (inklusive OAuth 2.0), verwahrt Zugangsdaten geschützt und führt eigenes Code‑Handling in einer isolierten Sandbox‑Umgebung aus. Zusätzlich ist Langdock ISO 27001‑zertifiziert, SOC 2 Type II-geprüft und vollständig DSGVO‑konform.
Sobald eine Integration verbunden ist, kannst du sie in jedem Chat direkt nutzen, indem du @ eingibst und verfügbare Actions auswählst. Außerdem können Agenten dank ihrer Anweisungen Integrationen automatisch ausführen.
