Microsoft Docs MCP Serveur

Qu'est-ce que le serveur MCP de Microsoft Learn Docs ?

Le serveur MCP de Microsoft Learn Docs est un service basé sur le cloud conçu pour alimenter des outils d'IA comme GitHub Copilot et Cursor avec un accès en temps réel à la documentation Microsoft de confiance. En adoptant la norme Model Context Protocol (MCP), il permet à toute IA compatible MCP de fonder ses réponses sur du contenu officiel de Microsoft.

Capacités Clés

Récupération de Contenu de Haute Qualité

Recherche efficacement à travers Microsoft Learn, Azure, Microsoft 365 et d'autres documentations officielles de Microsoft pour retourner les informations les plus pertinentes.

Compréhension Sémantique

Tire parti d'une recherche sémantique avancée basée sur des vecteurs pour fournir des résultats contextuellement précis adaptés à l'intention de l'utilisateur.

Optimisation du Découpage

Retourne jusqu'à 10 morceaux de contenu concis et de haute qualité (chacun pouvant contenir jusqu'à 500 tokens), y compris les titres d'articles, les URL et des extraits bien structurés.

Mises à Jour en Temps Réel

Se synchronise en continu avec la dernière documentation Microsoft dès sa publication, garantissant des réponses toujours à jour.

🌟 Microsoft Learn Docs MCP Server

The Microsoft Learn Docs MCP Server implements the Model Context Protocol (MCP) server that provides AI assistants with real-time access to official Microsoft documentation.

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

📑 Table of contents

🎯 Overview
🌐 The Microsoft Learn Docs MCP Server Endpoint
🛠️ Currently Supported Tools
🔌 Installation & Getting Started
❓ Troubleshooting
🔮 Future Enhancements
📚 Additional Resources

🎯 Overview

✨ What is the Microsoft Learn Docs MCP Server?

The Microsoft Docs MCP Server is a cloud-hosted service that enables MCP hosts like GitHub Copilot and Cursor to search and retrieve accurate information directly from Microsoft's official documentation. By implementing the standardized Model Context Protocol (MCP), this service allows any compatible AI system to ground its responses in authoritative Microsoft content.

📊 Key Capabilities

High-Quality Content Retrieval: Search and retrieve relevant content from Microsoft Learn, Azure documentation, Microsoft 365 documentation, and other official Microsoft sources.
Semantic Understanding: Uses advanced vector search to find the most contextually relevant documentation for any query.
Optimized Chunking: Returns up to 10 high-quality content chunks (each max 500 tokens), with article titles, URLs, and self-contained content excerpts.
Real-time Updates: Access the latest Microsoft documentation as it's published.

🌐 The Microsoft Learn Docs MCP Server Endpoint

The Microsoft Learn Docs 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 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.

Example JSON configuration:

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

🛠️ Currently Supported Tools

Tool Name	Description	Input Parameters
`microsoft_docs_search`	Performs semantic search against Microsoft official technical documentation	`query` (string): The search query for retrieval

🔌 Installation & Getting Started

The Microsoft Learn Docs 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
Visual Studio	Manual configuration required<br/>Use `"type": "http"`	Visual Studio MCP Official Guide
Cursor IDE		Cursor MCP Official Guide
Roo Code	Manual configuration required<br/>Use `"type": "streamable-http"`	Roo Code MCP Official Guide
Cline	Manual configuration required<br/>Use `"type": "streamableHttp"`	Cline MCP Official Guide

Alternative Installation (for clients without Streamable HTTP support)

Some clients don't support Streamable HTTP, so you can use mcp-remote as a workaround:

Client	Manual Configuration	MCP Guide
Claude Desktop	<details><summary>View Config</summary><pre>{<br/> "microsoft.docs.mcp": {<br/> "command": "npx",<br/> "args": [<br/> "-y",<br/> "mcp-remote",<br/> "https://learn.microsoft.com/api/mcp"<br/> ]<br/> }<br/>}</pre> </details>	Claude Desktop MCP Guide
Windsurf	<details><summary>View Config</summary><pre>{<br/> "microsoft.docs.mcp": {<br/> "command": "npx",<br/> "args": [<br/> "-y",<br/> "mcp-remote",<br/> "https://learn.microsoft.com/api/mcp"<br/> ]<br/> }<br/>}</pre> </details>	Windsurf MCP Guide

▶️ Getting Started

Open GitHub Copilot in VS Code and switch to Agent mode
You should see the Learn Docs MCP Server in the list of tools
Try a prompt that tells the agent to use the Docs MCP Server, such as "what are the az cli commands to create an Azure container app according to official Microsoft Learn documentation?"
The agent should be able to use the Docs MCP Server tools to complete your query

❓ Troubleshooting

⚠️ Common Issues

Issue	Possible Solution
Connection errors	Verify your network connection and that the server URL is correctly entered
No results returned	Try rephrasing your query with more specific technical terms
Tool not appearing in VS Code	Restart VS Code or check that the MCP extension is properly installed
HTTP status 405	Method not allowed happens when a browser tries to connect to the endpoint. Try using the Docs MCP Server through VS Code GitHub Copilot or MCP Inspector instead.