MCP

🚀 Microsoft Learn MCP Server

The Microsoft Learn MCP Server is a remote MCP Server. It enables clients like GitHub Copilot and other AI agents to directly obtain trusted and up - to - date information from Microsoft's official documentation. It supports streamable http transport, which is lightweight for clients to use.

Please note that this project is in Public Preview and implementation may significantly change prior to our General Availability.

🚀 Quick Start

Installation

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

Client	One - click Installation	MCP Guide
VS Code		VS Code MCP Official Guide
Claude Desktop	View Instructions 1. Open Claude Desktop 2. Go to Settings → Integrations 3. Click Add Integration 4. Enter URL: https://learn.microsoft.com/api/mcp 5. Click Connect	Claude Desktop Remote MCP Guide
Claude Code	View Instructions 1. Open a CLI 2. Type claude mcp add --transport http microsoft_docs_mcp https://learn.microsoft.com/api/mcp and press enter 3. (optional) Type --scope user directly after claude mcp add to make this MCP server available in Claude Code for all of your projects	Claude Code Remote MCP Guide
Visual Studio	Manual configuration required Use "type": "http"	Visual Studio MCP Official Guide
Cursor IDE		Cursor MCP Official Guide
Roo Code	Manual configuration required Use "type": "streamable-http"	Roo Code MCP Official Guide
Cline	Manual configuration required Use "type": "streamableHttp"	Cline MCP Official Guide
Gemini CLI	Manual configuration required View Config Note: Add an mcpServer object to .gemini/settings.json file { "Microsoft Learn MCP Server": { "httpUrl": "https://learn.microsoft.com/api/mcp" } }	How to set up your MCP server
Qwen Code	Manual configuration required View Config Note: Add an mcpServer object to .qwen/settings.json file { "Microsoft Learn MCP Server": { "httpUrl": "https://learn.microsoft.com/api/mcp" } }	Configure the MCP server in settings.json
GitHub	Manual configuration required View Config Note: Navigate to Settings → Coding agent { "mslearn": { "command": "npx", "args": [ "-y", "mcp-remote", "https://learn.microsoft.com/api/mcp" ], "tools":["*"] } }
ChatGPT	Manual configuration required View Instructions 1. Open ChatGPT in the browser 2. Go to Settings → Connectors → Advanced settings → Turn Developer mode on 3. Go back to connectors and click create 4. Give the connector a name, enter URL https://learn.microsoft.com/api/mcp, set authentication to No authentication and trust the application 5. Click create	ChatGPT Official Guide

Alternative Installation (for legacy clients or local configuration)

For clients that don't support native remote MCP servers or if you prefer local configuration, you can use mcp-remote as a proxy:

{
  "microsoft.docs.mcp": {
    "command": "npx",
    "args": [
      "-y",
      "mcp-remote",
      "https://learn.microsoft.com/api/mcp"
    ]
  }
}

{
  "microsoft.docs.mcp": {
    "command": "npx",
    "args": [
      "-y",
      "mcp-remote",
      "https://learn.microsoft.com/api/mcp"
    ]
  }
}

{
  "microsoft.docs.mcp": {
    "command": "npx",
    "args": [
      "-y",
      "mcp-remote",
      "https://learn.microsoft.com/api/mcp"
    ]
  }
}

▶️ Getting Started

1. For VS Code: Open GitHub Copilot in VS Code and switch to Agent mode
2. For Claude Desktop: After adding the integration, you'll see the MCP tools icon in the chat interface
3. You should see the Learn MCP Server in the list of available tools
4. Try a prompt that tells the agent to use the MCP Server, such as "what are the az cli commands to create an Azure container app according to official Microsoft Learn documentation?"
5. The agent should be able to use the MCP Server tools to complete your query

✨ Features

✨ Example Prompts: Your Source of Truth

Your AI assistant should automatically use these tools for Microsoft - related topics. With both search and fetch capabilities, you can get quick answers or comprehensive deep dives. To ensure that it always consults the official documentation, you can add phrases like search Microsoft docs, deep dive, fetch full doc.

Quick Search & Reference

"Give me the Azure CLI commands to create an Azure Container App with a managed identity. search Microsoft docs"

"Is gpt - 4.1 - mini available in EU regions? fetch full doc"

Code Verification & Best Practices

"Are you sure this is the right way to implement IHttpClientFactory in a .NET 8 minimal API? search Microsoft docs and fetch full doc"

"Show me the complete guide for implementing authentication in ASP.NET Core. fetch full doc"

Comprehensive Learning & Deep Dive

"I need to understand Azure Functions end - to - end. search Microsoft docs and deep dive"

"Get me the full step - by - step tutorial for deploying a .NET application to Azure App Service. search Microsoft docs and deep dive"

📊 Key Capabilities

• High - Quality Content Retrieval: Search and retrieve relevant content from Microsoft's official documentation in markdown format.
• Semantic Understanding: Uses advanced vector search to find the most contextually relevant documentation for any query.
• Real - time Updates: Access the latest Microsoft documentation as it's published.

📦 Installation

The installation methods are detailed in the Quick Start section, including one - click installation for multiple clients and alternative installation for legacy clients or local configuration.

💻 Usage Examples

Basic Usage

Use prompts with phrases like search Microsoft docs, deep dive, fetch full doc to let the AI assistant use the MCP Server tools. For example:

"what are the az cli commands to create an Azure container app according to official Microsoft Learn documentation?"

Advanced Usage

When dealing with complex questions about Microsoft technologies, such as "Are you sure this is the right way to implement IHttpClientFactory in a .NET 8 minimal API? search Microsoft docs and fetch full doc", the AI assistant can use the microsoft_docs_search and microsoft_docs_fetch tools to get detailed information from the official documentation.

📚 Documentation

🌐 The Microsoft Learn MCP Server Endpoint

The Microsoft Learn MCP Server is accessible to any IDE, agent, or tool that supports the Model Context Protocol (MCP). Any compatible client can connect to the following remote MCP endpoint:

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

Note: This URL is intended for use within a compliant MCP client via Streamable HTTP, such as the recommended clients listed in our Quick Start section. It does not support direct access from a web browser and may return a 405 Method Not Allowed error if accessed manually. For developers who need to build their own solution, please follow the mandatory guidelines in the Building a Custom Client section to ensure your implementation is resilient and supported.

Example JSON configuration:

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

🛠️ Currently Supported Tools

❓ Troubleshooting

💻 System Prompt

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 utilize microsoft.docs.mcp more frequently:

## Querying Microsoft Documentation

You have access to MCP tools called `microsoft_docs_search` and `microsoft_docs_fetch` - these tools allow you to search through and fetch Microsoft's latest official documentation, 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 this tool for research purposes when dealing with specific / narrowly defined questions that may occur.

⚠️ Common Issues

🆘 Getting Support

• Ask questions, share ideas
• Create an issue

🔮 Future Enhancements

The Microsoft Learn MCP Server team is working on several enhancements:

• microsoft_code_search tool: Helps agents find precise, official Microsoft sample code snippets
• Improved telemetry to help inform server enhancements
• Expanding coverage to additional Microsoft documentation sources
• Improved query understanding for more precise results

📚 Additional Resources

• Microsoft Learn MCP Server product documentation
• Microsoft MCP Servers
• Microsoft Learn
• Model Context Protocol Specification

🔧 Technical Details

⚠️ Building a Custom Client

If your use case requires a direct, programmatic integration, it is essential to understand that MCP is a dynamic 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:

1. Discover Tools Dynamically: Your client should fetch current tool definitions from the server at runtime (e.g., using tools/list). Do not hard - code tool names or parameters.
2. Refresh on Failure: Your client should handle errors during tool/invoke calls. 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 calling tools/list.
3. Handle Live Updates: Your client should listen for server notifications (e.g., listChanged) and refresh its tool cache accordingly.