Microsoft Learn MCP Server

{ "servers": { "microsoft-learn": { "type": "http", "url": "https://learn.microsoft.com/api/mcp" } } }

The Microsoft Learn MCP Server offers experimental features that are under active development. These features may change or be refined based on user feedback and usage patterns.

For applications that require OpenAI Deep Research model compatibility, you can use the OpenAI-compatible endpoint:

https://learn.microsoft.com/api/mcp/openai-compatible

To manage token usage and control costs, you can append themaxTokenBudgetquery parameter to the MCP endpoint URL. This parameter limits the token count in search tool responses by truncating the content to meet your specified budget.

https://learn.microsoft.com/api/mcp?maxTokenBudget=2000

# Run instantly (no install) npx @microsoft/learn-cli search "azure functions timeout" # Or install globally npm install -g @microsoft/learn-cli # then use mslearn mslearn search "azure functions timeout"

Pass--jsonto get structured JSON output, useful for programmatic processing:

These agent skills are packed in amicrosoft-docsplugin together with the Learn MCP server itself. If you use Claude Code, run the following command and restart Claude Code:

/plugin install microsoft-docs@claude-plugins-official

Agent Skills work across multiple AI agents:

The Microsoft Learn MCP Server supports quick installation across multiple development environments. Choose your preferred client below for streamlined setup:

If your use case requires a direct, programmatic integration, it is essential to understand that MCP is adynamic protocol, not a static API. The available tools and their schemas will evolve.

To build a resilient client that will not break as the service is updated, you should adhere to the following principles:
- Discover Tools Dynamically:Your client should fetch current tool definitions from the server at runtime (e.g., usingtools/list).Do not hard-code tool names or parameters.
- Refresh on Failure:Your client should handle errors duringtool/invokecalls. If a tool call fails with an error indicating it is missing or its schema has changed (e.g., an HTTP 404 or 400 error), your client should assume its cache is stale and automatically trigger a refresh by callingtools/list.
- Handle Live Updates:Your client should listen for server notifications (e.g.,listChanged) and refresh its tool cache accordingly.

Even tool-friendly models like Claude Sonnet 4 sometimes fail to call MCP tools by default; use system prompts to encourage usage.

Here's an example of a Cursor rule (a system prompt) that will cause the LLM to utilizemicrosoft-learnmore frequently:

## Querying Microsoft Documentation You have access to MCP tools called microsoft_docs_search, microsoft_docs_fetch, and microsoft_code_sample_search - these tools allow you to search through and fetch Microsoft's latest official documentation and code samples, and that information might be more detailed or newer than what's in your training data set. When handling questions around how to work with native Microsoft technologies, such as C#, F#, ASP.NET Core, Microsoft.Extensions, NuGet, Entity Framework, the dotnet runtime - please use these tools for research purposes when dealing with specific / narrowly defined questions that may occur.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Connect AI tools like Cursor and VS Code to your product documentation using the Biel.ai platform.

The official Duck Framework MCP server provides AI assistants with rich, project-aware context for building applications using Duck Framework. It offers documentation retrieval, code guidance, API references, best practices, component discovery, and framework-specific recommendations to help developers generate high-quality Duck Framework projects faster and more accurately.

MCP server for AI Diagram Maker — generate beautiful software engineering diagrams directly inside Cursor, Claude Desktop, Claude Code, or any MCP-compatible AI agent

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.

Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

Remote, no-auth MCP server providing AI-powered codebase context and answers

Create and read feature flags, review experiments, generate flag types, search docs, and interact with GrowthBook's feature flagging and experimentation platform.

Search and evaluate MCP servers from your AI agent: quality grades, live verification status, install commands and client compatibility for 5,000+ servers.