Share via


Microsoft Learn MCP Server overview

The Microsoft Learn MCP Server is a Model Context Protocol server that adds trusted and up-to-date Learn content as context to language models. It is a remote MCP server that uses streamable http. It lets AI agents send a query to Microsoft Learn and returns a JSON-encoded response with chunks of publicly available documentation.

Use cases

  • Enhance coding agents like GitHub Copilot with Learn content
  • Leverage Learn content in Copilot Studio agents, AI Foundry agents, or custom solutions
  • Use the knowledge search in a way tailored to your needs.

How the Learn MCP Server works

Learn MCP Server is a remote MCP server that uses streamable http. Compatible client apps like GitHub Copilot can connect with the endpoint.

https://learn.microsoft.com/api/mcp

Note: This endpoint is designed for programmatic access by MCP clients via Streamable HTTP. It does not support direct access from a web browser and may return a 405 Method Not Allowed error if accessed manually.

The MCP server provides an interface to the Learn knowledge service, that powers Ask Learn and Copilot for Azure. Developer options are listed in the Microsoft Learn MCP Server developer documentation. We also have release notes to see what the latest updates are, and best practices information. If you are interested in using it, check out the Get Started with the Microsoft Learn MCP Server article.

Requirements

When you use the Learn MCP Server, you agree with Microsoft Learn and Microsoft API Terms of Use.

There's no authentication required to access the Microsoft Learn MCP Server. Users can use their preferred MCP client or agentic IDE, such as VS Code, Visual Studio, MCP inspector, etc.

Availability and pricing

The Microsoft Learn MCP Server is publicly available and offered under the term of the Microsoft APIs Terms of Use. There's no charge to use the MCP server.

Limitations

  • The MCP server contains publicly available documentation. It doesn't contain content from training modules, learning paths, instructor-led courses, and exams at this time, which is available through the Learn Catalog API.
  • The underlying knowledge service refreshes incrementally per content update and completely once a day.
  • Updates to the MCP server will be communicated via updates to the Learn MCP Server Release Notes.

Next steps

You can learn more about the Learn MCP Server by visiting the following links: