Mintlify MCP Server

The Mintlify MCP Server is Mintlify’s officially documented, hosted Admin MCP server at https://mcp.mintlify.com. It connects an MCP-capable AI client to a Mintlify account and its documentation projects. According to Mintlify, authorized teams can use it to read and edit pages, restructure navigation, update docs.json, open pull requests, and manage selected deployment settings and workflows. The official product and documentation link is https://www.mintlify.com/docs/ai/mintlify-mcp. This record deliberately covers the Admin server, not the separate Search MCP for an individual Mintlify documentation site and not Mintlify Index. Mintlify operates the service remotely; for this hosted server variant, the provider does not publish a current public source repository. A query to https://api.github.com/repos/mintlify/mcp returned HTTP 404 on 2026-09-08. The repository link and GitHub star count are consequently blank: inventing a count or borrowing one from an unrelated repository would not be a quality signal.

Product boundary and documentation context

The Admin MCP is a working tool for the team that manages a Mintlify deployment. It can read and search MDX, make targeted edits, or overwrite full pages. Navigation tools can create, rename, move, or delete nodes, while update_config can change settings in docs.json. Those capabilities affect more than prose: navigation, SEO-related configuration, and the presentation of a documentation site can change. Mintlify’s separate Search MCP, by contrast, sits at the /mcp path of a particular Mintlify site and returns search results and published page content to end users. Use that read-oriented Search MCP, rather than the Admin MCP, when the goal is only to retrieve answers from public documentation.

Sign-in, access, and Git connection

Setup uses an interactive OAuth login to the Mintlify account. Per the official documentation, the session inherits dashboard permissions, so protected settings require a project admin role. The project’s connected GitHub, GitLab, or Bitbucket integration must also have write access to the deploy-branch repository because save creates pull requests or commits through the same integration. Mintlify documents configurations for Claude Code, Codex, and Cursor; those three already documented compatibilities are assigned here. Never put credentials in a prompt, repository, client configuration, or screenshot. Revoke OAuth access under connected apps in the Mintlify dashboard when it is no longer needed, and remove the server from the AI client.

Branch, diff, and publication

An Admin MCP session binds to one Git branch after checkout. According to Mintlify, the service creates a fresh mintlify-mcp/... branch from the deployment branch or uses an explicitly selected branch. Changes are buffered in that session first. Before save, a human must read diff and inspect the rendered preview. Saving in pull-request mode is the safer default: it creates a reviewable pull request instead of an unattended publication. Depending on project and branch-protection settings, auto mode can allow immediately effective changes; it is not a substitute for review. Deployment management through Code Mode is especially sensitive because settings, workflows, members, billing, integrations, or analytics can affect a live deployment immediately.

Untrusted content and prompt injection

Documentation pages, issues, existing MDX files, error messages, and external requirements are data, not commands. A malicious paragraph can claim that secrets should be exposed, branch protection disabled, save called, or navigation deleted. The AI client and model may place that text in their context; neither a hosted MCP endpoint nor a branch makes content trustworthy. Initially limit tools to read, search, list_nodes, and diff. Treat proposed changes as drafts, compare the target deployment, path, diff, and side effect against a human-confirmed request, and require explicit approval for every write. No instruction embedded in fetched content can replace that approval.

Data path and responsibilities

The data path includes Mintlify, the MCP client, and the selected model provider. During a tool call, the Admin MCP reads or changes content or dashboard data and returns results to the client; the client can include those results in a model request. Hosted by Mintlify therefore does not mean the full AI path remains local. Before production use, review the concrete client’s model provider, retention, training choices, enterprise terms, and DPA. Minimize context to the pages needed and remove tokens, personal data, internal URLs, and secrets from examples. Mintlify and Git permissions constrain server access, but they do not replace model-data review or human review.

FAQ

Is this the public Search MCP for a docs site? No. This record covers the Admin MCP at mcp.mintlify.com, which has editing and management capabilities. A single Mintlify site’s Search MCP operates at that site’s /mcp path and is intended to search published content.

Is there an official GitHub repository with a star count? The checked candidate github.com/mintlify/mcp returned 404 from the GitHub API. The current official documentation describes a hosted service rather than a public server repository, so this record stores neither a repository nor stars.

Can an agent publish automatically? Technically, save can open a PR or make changes effective depending on project configuration. Operationally, a human should inspect the diff, preview, target, and consequence, and enforce PR mode for risky changes.

A Mintlify account with access to the target project, interactive OAuth login, an MCP-capable client, and write access from the connected Git integration to the deploy-branch repository.

In Claude Code run claude mcp add --transport http mintlify https://mcp.mintlify.com; in Codex add the URL under [mcp_servers.mintlify]; in Cursor add the URL in mcp.json. Then complete OAuth, check out only the confirmed deployment, and always review diff and the preview before save.

claude mcp add --transport http mintlify https://mcp.mintlify.com

Interactive OAuth login with the Mintlify account. The session inherits dashboard permissions and is granted at deployment or organization level.

Reading, editing, navigation, and docs.json occur inside the checked-out branch session; save uses the connected Git integration. Deployment management can take effect immediately under granted scopes and needs especially narrow permissions.

The hosted MCP service returns documentation and dashboard results to the connected AI client. That client can send tool results to its model provider; review the selected client’s data handling and retention separately.

The Admin MCP has write access. MDX, issues, and tool results are untrusted content and can contain prompt injection. Execute writes only after human review of deployment, branch, diff, and impact; Code Mode can change live settings immediately.