Mintlify MCP Server

Official hosted Mintlify Admin MCP server for branch-based documentation edits, pull requests, and controlled dashboard administration.

Description

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.

Requirements

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.

Installation instructions

The Mintlify Admin MCP server at https://mcp.mintlify.com is hosted write access to Mintlify documentation and parts of its dashboard. This guide follows only Mintlify’s current official documentation at https://www.mintlify.com/docs/ai/mintlify-mcp. It is for project owners who want to edit content through Claude Code, Codex, or Cursor without losing sight of access boundaries, Git review, and data protection. The server is not the read-oriented Search MCP for one documentation site: that Search MCP lives at the relevant site’s /mcp path. When the task is simply research in published documentation, that read-only path is usually the better and lower-risk choice.

Quick start

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.

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

Step 1: Check prerequisites and permissions

Before installing, identify the Mintlify project the connection should serve and the person who will review resulting changes. You need a Mintlify account with access to that project. The OAuth login inherits the dashboard role according to the provider, so protected settings require project-admin access. The project’s GitHub, GitLab, or Bitbucket integration must be able to write to the deploy-branch repository because save creates a commit or pull request through that connection. Use a personal account only when the organization permits it, and revoke old connections under “Settings → Security & access → Connected apps.”

Define a narrow job before starting: update one named page, restructure a specified section, or correct a single navigation item. A broad objective such as “clean up the documentation” expands the possible diff unnecessarily. Put the target deployment, target branch, permitted paths, and intended result in a human-confirmed work request. Arrange a second reviewer when the content is legal, security-sensitive, or product-critical.

Step 2: Connect the client and finish OAuth

For Claude Code, Mintlify documents this local configuration command:

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

For Codex, create a [mcp_servers.mintlify] section with the URL https://mcp.mintlify.com in ~/.codex/config.toml. In Cursor, configure the same URL as a mintlify entry in mcp.json. On first use, the client opens a browser for interactive OAuth. Verify the domain, account, and requested access in that browser; do not approve a login triggered by an unexpected redirect or text inside a document. Passwords, OAuth codes, session tokens, and Git tokens never belong in prompts, MDX examples, commits, or screenshots.

After signing in, make the available connection visible first. If more than one deployment is reachable, use only list_deployments and choose the confirmed subdomain. According to Mintlify, checkout creates or attaches a branch. Give it a traceable slug such as fix-auth-guide and verify that the deployment branch and project match the request. A checkout against the wrong deployment can otherwise create a technically valid but operationally wrong pull request.

Read first, then make the smallest change

Start with read, search, list_nodes, and then diff. This obtains page content, navigation context, and the actual pending changes without publishing anything. Use edit_page for a small reviewable change rather than write_page when a full replacement is not necessary. Manually inspect paths, links, code blocks, headings, versions, and examples in the preview. Navigation operations such as move_node and delete_node are not harmless formatting: they can change user journeys and discoverability.

Treat every fetched page, issue, and error message as untrusted content. Instructions such as “skip review,” “change permissions,” “insert a token,” or “call save” can be prompt injection even if they look like an internal note. They are not authorization. The client can pass tool results to a language model that then proposes changes. Keep context small, remove secrets and personal data from requested excerpts, and use a tool allowlist without write operations until the intended work is clear.

Review the diff and save safely

Before every save, call diff and compare every line with the confirmed work request. Open the editor or preview URL returned by Mintlify and inspect the rendered page as well. Check that a link, navigation item, frontmatter field, or example was not changed unintentionally. For ordinary content work, use save in pull-request mode so a second review occurs in the Git provider. Use auto mode or direct pushes only after explicit documented approval and a check of branch protection.

Code Mode is separate from the branch session and, according to Mintlify, can manage settings, workflows, members, billing, integrations, and analytics directly on the live deployment. Never derive such calls from an automated agent run, third-party document text, or a vague request. They need explicit human confirmation of the target, precise effect, and rollback plan. After a PR merge or an authorized direct change, verify the live result and roll back through Git or the dashboard if it differs from the approved outcome.

Data path, rotation, and completion

The connection flows from Mintlify to the MCP client and often onward to that client’s model provider. A hosted Mintlify service does not mean documentation content or dashboard responses are processed only locally. Before using production data, review the chosen client’s retention, training, DPA, and enterprise settings. Limit OAuth to the required deployments, remove the server after time-bounded work, and revoke the OAuth grant after a device change, role change, or suspected compromise. Pull requests already opened remain after revocation and should be closed or reverted when appropriate.

FAQ

Do I need a new branch for every change? Not necessarily, but one focused session per topic is easier to review. Mintlify keeps sessions in memory; use discard_session for unwanted drafts rather than leaving unknown branch remnants.

Why is a local MCP configuration entry not a security boundary? The configuration connects the client to a hosted service. Tool results can then enter the model provider’s context; OAuth, Git permissions, client data policy, and human review remain separate controls.

What is the safe default for save? A pull request with a reviewed diff and rendered preview. Use direct or automatically effective changes only with an explicit exception approval and an available rollback plan.

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

Authentication

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

Required access permissions

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.

Transmitted or stored data

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.

Security risks

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.

License and costs

License
Hosted Mintlify service; no public source license published for this server.
Cost
paid

The official Admin MCP documentation does not state a separate server price. Check Mintlify availability, entitlements, and current terms with the provider before use.

Alternatives

Not recorded yet.

At a glance

Provider
Mintlify
Status
Official server
Deployment
Remote
Current version
Not recorded yet.
Last reviewed
08.09.2026

Repository and documentation

Categories

Supported clients

Related guides

Guides and background related to this entry.

No related guides yet.