Mintlify

Connect Mintlify to Copilot Studio

Search, read and write Mintlify from Copilot Studio. Arlet links the two through one MCP connection and takes care of keys and authentication.

Arlet makes Mintlify's official admin MCP server available from the AI client you already use. Signing in with your Mintlify account completes the connection.

The AI can read and edit documentation pages, restructure navigation and update docs.json. Edits accumulate on a session branch and ship as a pull request when saved, so you can review before merging. Deployment-management calls apply immediately, so keep tool-call confirmation enabled in your AI client. The available tools are those provided by Mintlify's official server.

How to connect Mintlify to Copilot Studio

  1. 1

    In the Arlet dashboard, open Integrations → Add an integration and choose Mintlify. Sign in with Link Mintlify, name the connection and click Create.

  2. 2

    Sign in to Copilot Studio with your work account, create a new agent (or open an existing one), and in the Build tab choose Tools → + → Add → Model Context Protocol (MCP) in the right panel.

  3. 3

    In the Add MCP server form, enter "Arlet" as the Server name, https://mcp.arlet.dev/mcp/ as the Server URL, choose OAuth 2.0 for Authentication and "Dynamic (detected)" for Configuration type, then click Add. No Client ID / Secret is needed.

  4. 4

    On the Select a connection screen, choose Create new connection → Create, then sign in with Google on the Arlet authorization screen and click Allow. Click Add to attach the tool to the agent, then Publish to use it from Microsoft 365 Copilot.

Requires a Microsoft work account and a Copilot Studio license (or trial). MCP is available only for agents using generative orchestration and not in Copilot Studio in Teams.

What you can do

Mintlify tools that Copilot Studio can call.

  • list_deployments

    List the documentation deployments (sites) this connection can access.

  • checkout

    Open an editing session on a branch and get the editor URL.

  • read

    Read a page's MDX body.

  • search

    Search files in the session by string or regex.

  • list_nodes

    Read the navigation tree (pages, groups, tabs).

  • edit_page

    Edit a page with targeted string replacements.

  • write_page

    Overwrite a page's full content.

  • create_node

    Add pages, groups or tabs to the navigation.

  • update_node

    Change a page's title, frontmatter or navigation properties.

  • move_node

    Move pages or groups within the navigation.

  • delete_node

    Remove pages or groups from the navigation.

  • update_config

    Change docs.json (site configuration).

  • diff

    Show the session's changes against the deploy branch.

  • save

    Ship the session's changes as a pull request (or a commit to an existing branch).

  • discard_session

    Drop the session's changes.

  • list_branches

    List the docs repository's branches.

  • execute_code

    Manage deployment settings (workflows, members, integrations, analytics) with code. Applies immediately.

The tool list follows what Mintlify's official MCP server provides and may change.

Example uses

  • Fix the docs

    Find outdated statements or typos, fix them and open a pull request to review before merging.

  • Write a new page

    Draft a page from a spec or change notes and add it to the right group in the navigation.

  • Tidy the structure

    Reorder pages and groups and make titles and descriptions consistent.

  • Change site settings

    Update the theme or navigation in docs.json and review it in a pull request.

Prompts you can use as-is

  • Find pages that mention the v1 API and open a pull request changing them to the v2 API
  • Write a Slack integration page from these change notes and add it to the Integrations group
  • Reorder the Getting started group for readability and make the titles consistent
  • Add an API reference tab to the navigation in docs.json

Use Mintlify with other AI clients