Microsoft 365 Copilot MCP Server

Note: This is an unofficial MCP server, but developed by Microsoft engineers, integrating the latest Microsoft 365 Copilot APIs. We welcome your feedback and contributions!

Connect your AI assistant to Microsoft 365 through the Model Context Protocol (MCP). This server enables AI tools to access your SharePoint documents, OneDrive files, emails, Teams conversations, and more - all while respecting your organization's access controls.

Overview

The m365-copilot-mcp server provides three powerful capabilities for AI assistants:

Learn more: These capabilities are built on the official Microsoft 365 Copilot APIs.

Prerequisites

• Node.js 20+ - Runtime environment

• Microsoft 365 account - With Microsoft 365 Copilot license

• MCP-compatible AI tool - Such as Claude Code, GitHub Copilot, or any other MCP client

Video Tutorials

Learn how to install and use the M365 Copilot MCP Server with these step-by-step video guides:

📺 Claude Code with M365 Copilot MCP Server

Click the image above to watch the tutorial on how to install and use the M365 Copilot MCP Server with Claude Code.

📺 GitHub Copilot with M365 Copilot MCP Server

Click the image above to watch the tutorial on how to install and use the M365 Copilot MCP Server with GitHub Copilot in VS Code.

Configuration

Configure the MCP server in your AI tool's settings. The server uses npx to run directly from npm without requiring global installation.

Claude Code

Add the server using the Claude Code CLI:

macOS/Linux:

Windows:

The -y flag automatically accepts prompts, and npx will download and run the latest version of the package.

GitHub Copilot (VS Code)

Create a .vscode/mcp.json file in your project root, or add to your VS Code user settings:

Option 1: Project-level configuration (.vscode/mcp.json):

Option 2: User-level configuration (VS Code settings.json):

Requirements: VS Code 1.99+ with GitHub Copilot extension installed.

Other MCP Clients

For other MCP-compatible tools, use the following command with npx:

Refer to your specific AI tool's documentation for MCP server configuration instructions.

Authentication

On first use, the server will automatically open your browser for Microsoft 365 authentication. After signing in once, your credentials are securely cached locally - no need to sign in again.

Headless Environments (Linux Servers)

No configuration needed! If you're running the MCP server on a headless Linux server without a browser, the server will automatically detect this and fall back to Device Code Flow:

1. The server will display a URL (https://microsoft.com/devicelogin) and a code in the console

2. Open the URL on any device with a browser (phone, laptop, etc.)

3. Enter the code and sign in with your Microsoft 365 account

4. The server will automatically complete authentication

This happens automatically - just run the same configuration as on any other platform.

Security & Privacy

Your data is safe. The MCP server:

• ✅ Only reads data through official Microsoft Graph APIs

• ✅ Respects your organization's access controls and permissions

• ✅ Stores authentication tokens locally on your machine (encrypted)

• ✅ Does NOT store, collect, or transmit any of your M365 content

• ✅ Makes direct API calls to Microsoft - no third-party servers involved

Using Your Own Azure AD App (Optional)

If you have security concerns or organizational requirements, you can use your own Azure AD application instead of the built-in one. However, this is completely optional - the default configuration is secure and sufficient for most users.

Azure AD App Registration Setup

When creating your own Azure AD app, you must register the redirect URI in your app registration:

1. Go to Azure Portal → Azure Active Directory → App registrations

2. Select your application (or create a new one)

3. Navigate to Authentication → Add a platform → Mobile and desktop applications

4. Add the redirect URI: http://localhost

5. Save the configuration

Note: The default redirect URI is http://localhost. Azure AD will match this URI regardless of the actual port used by the application, making it work seamlessly with dynamic port allocation. You can customize it using the REDIRECT_URI environment variable if needed (e.g., https://login.microsoftonline.com/common/oauth2/nativeclient).

Configuration

To use a custom Azure AD app, provide environment variables during configuration:

Claude Code

macOS/Linux:

Windows:

GitHub Copilot (VS Code)

Add environment variables to your configuration:

Optional Environment Variables:

• REDIRECT_URI: Custom redirect URI (default: http://localhost, alternative: https://login.microsoftonline.com/common/oauth2/nativeclient)

Required Microsoft Graph API Permissions:

• Sites.Read.All

• Files.Read.All

• Mail.Read

• Chat.Read

• ChannelMessage.Read.All

• OnlineMeetingTranscript.Read.All

• People.Read.All

• ExternalItem.Read.All

Available Tools

Your AI assistant can now use these three tools to interact with your M365 content:

1. m365copilotretrieval

Retrieves relevant text excerpts from your SharePoint and OneDrive content to answer questions.

Best for:

• Answering questions based on your documents

• Finding information buried in your content

• Grounding AI responses in your actual data

Example prompts:

• "What are the Q4 project deadlines mentioned in my documents?"

• "Summarize the team's decision about the new feature"

• "What does our company policy say about remote work?"

2. m365copilotsearch

Searches across your M365 environment to find specific documents and files.

Best for:

• Locating specific documents

• Getting document links to open or share

• Discovering relevant files across SharePoint and OneDrive

Example prompts:

• "Find the VPN setup guide"

• "Search for the Q4 budget spreadsheet"

• "Locate documents about network security policies"

3. m365copilotchat

Enables conversational interactions with Microsoft 365 Copilot, with awareness of your calendar, tasks, and content.

Best for:

• Asking about your schedule and meetings

• Getting summaries of recent activities

• Time-aware queries that need context

Example prompts:

• "What meetings do I have tomorrow?"

• "Summarize recent discussions about the product launch"

• "What are my action items for this week?"

Note: This tool requires your timezone in IANA format (e.g., "America/New_York", "Europe/London", "Asia/Shanghai").

Account Management

Switching Accounts (m365copilotlogout)

If you need to switch to a different Microsoft 365 account, you can use the logout tool to clear cached credentials.

How to use:

• Ask your AI assistant: "Logout from Microsoft 365" or "Switch to a different account"

• The tool will clear all cached authentication data

• Restart your MCP server for the logout to take full effect

• On next use, you'll be prompted to log in with a different account

This is useful for:

• Switching between work and personal M365 accounts

• Troubleshooting authentication issues

• Testing with different user permissions

How It Works

The MCP server acts as a secure bridge between your AI assistant and Microsoft 365, using official Microsoft APIs to access your data based on your permissions.

Troubleshooting

Authentication Issues

Problem: Want to switch to a different Microsoft 365 account Solution: Use the m365copilotlogout tool to clear cached credentials, then restart the MCP server. On next use, you'll be prompted to log in with a different account.

Problem: Redirect URI mismatch error during authentication Solution: Ensure http://localhost is registered in your Azure AD app registration under Authentication → Mobile and desktop applications. Azure AD will match this URI regardless of the actual port used. If using a custom redirect URI, set the REDIRECT_URI environment variable to match your Azure AD configuration.

Problem: Browser doesn't open for login Solution:

• On headless systems (Linux servers), the server will automatically fall back to Device Code Flow

• Check console output for the authentication URL and code

• On systems with a browser, check firewall settings or try a custom redirect URI

Problem: "Permission denied" errors Solution: Ensure your Microsoft 365 account has access to the requested resources. If you recently changed permissions or accounts, try using the logout tool and re-authenticating.

Connection Issues

Problem: AI assistant can't find the MCP server Solution:

• Verify installation: npm list -g m365-copilot-mcp

• Check that Node.js 20+ is installed: node --version

• Restart your AI assistant

Tool Not Working

Problem: Chat tool fails with timezone error Solution: Ensure you provide timezone in IANA format (e.g., "America/New_York")

Problem: No results returned Solution: Verify you have access to M365 content and are signed in to the correct account

Supported Platforms

• ✅ Windows 10/11

• ✅ macOS 10.15+

• ✅ Linux (Ubuntu 20.04+, other distributions)

Feedback & Support

This project is actively maintained. We welcome your feedback and contributions!

• Report Issues: GitHub Issues

• Feature Requests: GitHub Discussions

• Project Documentation: GitHub Repository

• API Documentation: Microsoft 365 Copilot APIs

License

MIT License - see LICENSE file for details.

Developed by Microsoft engineers | Powered by Microsoft 365 Copilot APIs