Mintlify MCP Server
Connect Mintlify to your AI agents with the Mintlify MCP server.
Updated
What is Mintlify MCP?
The Mintlify MCP server is a Model Context Protocol server that connects Mintlify to AI agents and assistants as a set of tools. With it connected, an agent can work with Mintlify (documentation platform — author, search, and publish developer docs) directly — instead of you copying data in and out by hand.
It is a remote MCP server that uses OAuth, so you point your client at the server URL, authorize once, and the Mintlify tools become available to the model.
Connect the Mintlify MCP server
Connect Mintlify MCP to Claude Code
- 1
Add the server
Use `claude mcp add` with the Mintlify MCP server URL (or its `npx` command), following the official docs.
- 2
Authorize
Complete authentication (OAuth) so Claude Code can call the server.
- 3
Verify
Ask Claude to use a Mintlify tool to confirm the connection is live.
Connect Mintlify MCP to Cursor
- 1
Open MCP settings
In Cursor, go to Settings → MCP → Add new server.
- 2
Add Mintlify
Provide the Mintlify MCP server URL or command and complete authentication.
- 3
Test
Reference Mintlify from chat to confirm Cursor can reach the tools.
Sample use cases
A developer asks the agent to find the authentication docs for a specific API endpoint
It searches the Mintlify-powered docs site and returns the relevant page with authentication requirements and example requests.
An agent checks all internal links across the documentation for broken references
It reports which pages have dead links, what they point to, and suggests corrections — preventing 404s in published docs.
An agent retrieves API reference pages and compares them against the actual API schema
It flags discrepancies between documented and actual endpoint parameters, response shapes, and status codes.
An agent reviews the docs navigation structure to identify gaps in documentation coverage
It maps all pages and sections, highlighting features that are mentioned in marketing but missing from the docs.
An agent pulls the content of a getting-started guide for review before a product launch
It returns the full page content, making it easy to check accuracy, tone, and completeness without opening the docs site.
An agent searches the docs for every mention of a deprecated feature
It lists every page referencing the feature, helping the team plan which docs to update during the deprecation rollout.
An agent compares two versions of a docs page to identify what changed
It highlights added, removed, and modified sections — useful for reviewing docs changes alongside code PRs.
Using Mintlify MCP with Gamut
On Gamut, the Mintlify MCP server becomes a tool your agents use inside an automated, event-driven workflow — triggered by an event or a schedule, acting through Mintlify and your other connected MCP servers, with the connection managed by Gamut rather than a local config file.
Frequently asked questions
What is the Mintlify MCP server?
It is a Model Context Protocol server that exposes Mintlify to AI agents as tools so they can work with it (documentation platform — author, search, and publish developer docs).
How do I connect the Mintlify MCP server?
Point your MCP client (Claude, Cursor, or Gamut) at the Mintlify MCP server URL and complete authentication (OAuth). See the official documentation for the exact URL and scopes.
Can I use Mintlify MCP with Gamut?
Yes — Gamut supports the Mintlify MCP server, so your agents can use it as a tool in automated, triggered workflows.
Is the Mintlify MCP server free?
The MCP server itself is open-source. You need a Mintlify account to host your documentation site, and Mintlify offers free and paid tiers.
Is the Mintlify MCP server hosted or self-hosted?
The MCP server runs locally alongside your AI tool (e.g., Claude Code or Cursor) and connects to Mintlify's API. You self-host the server; Mintlify hosts the docs.
Can the Mintlify MCP server search documentation content?
Yes. Its primary use case is searching and retrieving documentation pages, making it easy for AI agents to find relevant docs, check for accuracy, and surface information without manual browsing.
Can I use it to update documentation content?
It depends on the server's write capabilities. Most Mintlify MCP implementations focus on reading and searching docs. For content edits, you typically update the source files (Markdown/MDX) in your docs repository.