Mintlify
Mintlify is a documentation platform. This toolkit exposes the Admin API for managing docs programmatically — trigger deployments and previews, run automations, drive the docs-editing agent, and export analytics (feedback, searches, views, visitors and assistant conversations).
Verdict
Common use cases
- Surface top search queries and click-through rates
- Export user feedback to prioritize doc improvements
- Trigger AI agent to update stale API examples
- Track human vs bot traffic across doc pages
- Review assistant conversation logs for support insights
Integration
- Vendor
- Mintlify
- Category
- developer-tools
- Auth
- API_KEY
- Tools
- 14
- Composio slug
mintlify
Tools
- Create Agent Job
Start a background documentation agent job from a natural-language prompt. The agent edits the connected docs repo and OPENS A PULL REQUEST if it changes files (DESTRUCTIVE; consumes credits). Returns an AgentJob; poll its id with MINTLIFY_
- Get Agent Job
Retrieve the status and details (status, PR link, model, source repo/ref) of a docs agent job. Poll this until status is completed, archived or failed. No pagination.
- Get Assistant Caller Stats
Get assistant query counts broken down by caller type (web, api, other, total) for a date range. Returns a single aggregate object; no pagination.
- Get Assistant Conversations
Export the AI assistant conversation history (question, answer, cited sources, resolution status) for a Mintlify project, optionally filtered by date. Returns one page of conversations plus a cursor to fetch the next page.
- Get Feedback
Export a project's user feedback (thumbs / contextual comments / agent feedback), optionally filtered by date, source and status. Returns one page plus a cursor to fetch the next.
- Get Feedback By Page
Get feedback counts (thumbs up/down, code, total) aggregated per documentation page path for a date range. Single page of results — this endpoint exposes no pagination cursor, so only the first page is available.
- Get Page Views
Export per-path and site-wide content view counts split by human vs AI traffic. Offset-paginated: returns one page of rows plus site-wide totals, the hasMore flag as has_more, and a next_offset to fetch the following page.
- Get Search Queries
Export documentation search terms ordered by hit count (with CTR and top clicked page). Returns one page plus a cursor to fetch the next; there is no more-flag, so stop paging once next_cursor is null.
- Get Unique Visitors
Export per-path and site-wide approximate distinct visitor counts split by human vs AI traffic. Offset-paginated: returns one page plus a `has_more` flag and the effective `next_offset` to fetch the following page.
- Get Update Status
Get the status and details (queued / in_progress / success / failure, logs, commit, screenshot) of a triggered deployment update by its statusId. Poll this with the statusId returned by MINTLIFY_TRIGGER_UPDATE.
- Send Agent Message
Send a follow-up instruction to an existing, in-progress docs agent job (asynchronous). Use to refine or continue work on a job created by create_agent_job. Returns the updated AgentJob; poll get_agent_job for progress. No pagination.
- Trigger Automation
Trigger a custom-schedule automation (workflow) to run immediately. Returns the schemaId, instanceId and jobId of the launched run. Only custom-schedule automations are triggerable (others return 400). Requires a Mintlify plan that includes
- Trigger Preview
Create or update a preview deployment of the docs project for a Git branch (redeploys if a preview already exists for that branch). Returns a statusId to poll with MINTLIFY_GET_UPDATE_STATUS and a previewUrl. Requires a Mintlify plan that i
- Trigger Update
Queue a production deployment of the docs project from its configured branch. Returns a statusId to poll with MINTLIFY_GET_UPDATE_STATUS. Requires a Mintlify plan that includes deployments (otherwise the API returns 401 'Please upgrade to a
Setup
Setup guide
- 11. In Switchy, navigate to Settings → Integrations → Developer Tools and click Connect next to Mintlify. 2. You'll be prompted to paste a Mintlify API key; generate one from your Mintlify dashboard under API Settings. 3. Grant the key read access to analytics endpoints and write access if you plan to use the agent job tool. 4. Click Save and wait for the green Connected badge. 5. Open any Project, type @Mintlify in the chat, and select it from the autocomplete menu. 6. Test the connection by asking '@Mintlify show me page views for the last 7 days' — you should see a table of paths and traffic counts. 7. To invoke the agent job tool, write '@Mintlify create an agent job to fix broken links in the API reference' and confirm the prompt; Mintlify will return a job ID you can poll with Get Agent Job.
What teammates see: by default, memories from Mintlify are scoped to the Project (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Projects have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
Top Search Terms
@Mintlify get search queries for the last 30 days and show me the top 10 by hit count with their click-through ratesOpen in a Project →
Feedback Triage
@Mintlify fetch all unresolved feedback from the past two weeks and group it by page pathOpen in a Project →
Traffic Breakdown
@Mintlify get page views for the last 7 days and show me the split between human and AI traffic for each pathOpen in a Project →
Agent PR for Outdated Docs
@Mintlify create an agent job to update all code snippets in the authentication guide to use the new SDK versionOpen in a Project →
Assistant Conversation Audit
@Mintlify get assistant conversations from the past 14 days and summarize the most common unresolved questionsOpen in a Project →