Microsoft Graph MCP
Enables AI assistants to interact with Microsoft 365 through the Microsoft Graph API, including searching Teams messages, managing chats, and sending messages.
README
Microsoft Graph MCP
A Model Context Protocol (MCP) server that connects AI assistants to Microsoft Graph API. Search Teams messages, manage chats, send messages, and interact with your Microsoft 365 environment through natural language in Claude and other AI assistants.
🚀 Quick Start
Configuration
Claude Code
Add the server using the Claude Code CLI:
claude mcp add -s user \
microsoft-graph \
npx mcp-microsoft-graph@latest \
-e "MS_GRAPH_CLIENT_ID=your_client_id" \
-e "MS_GRAPH_TENANT_ID=your_tenant_id"
Manual Configuration (Any MCP Client)
Alternatively, add this configuration to your MCP client's configuration file:
{
"mcpServers": {
"microsoft-graph": {
"command": "npx",
"args": ["mcp-microsoft-graph@latest"],
"type": "stdio",
"env": {
"MS_GRAPH_CLIENT_ID": "your_client_id",
"MS_GRAPH_TENANT_ID": "your_tenant_id"
}
}
}
}
Get Your Azure AD Credentials
To get your CLIENT_ID and TENANT_ID:
- Go to Azure Portal → Azure Active Directory → App registrations
- Click New registration
- Give it a name (e.g., "MCP Microsoft Graph")
- Set Supported account types to "Single tenant"
- Click Register
- Copy the Application (client) ID - this is your
MS_GRAPH_CLIENT_ID - Copy the Directory (tenant) ID - this is your
MS_GRAPH_TENANT_ID
Required Permissions
Configure these permissions in your Azure AD app:
- Go to API permissions → Add a permission → Microsoft Graph → Delegated permissions
- Add these permissions:
User.Read- Read user profileUser.ReadBasic.All- Read all users' basic profilesChat.ReadBasic- Read basic chat propertiesChat.ReadWrite- Read and write chatsChatMessage.Read- Read chat messagesChatMessage.Send- Send chat messages
- Click Grant admin consent (if you have admin rights)
Authenticate
Run the authentication command once to sign in:
npm run auth
This will open a browser window for you to sign in with your Microsoft account.
✨ Features
- 💬 Teams Chat Management - Search, create, and manage Teams chats
- 📨 Message Operations - Send messages, search conversations, get chat history
- 👥 User Discovery - Search users and get profile information
- 🔍 Powerful Search - Search across all Teams messages with KQL syntax
- 🎯 Smart Mentions - @mention users in messages
- 🔒 OAuth Authentication - Secure Azure AD authentication flow
- 🎨 Rich Formatting - Markdown support in messages
🛠️ Available Tools
The server provides 8 MCP tools for Microsoft Graph operations:
User Management
get_current_user- Get your own profile informationsearch_users- Search for users by name or emailget_user- Get detailed information about a specific user
Chat Operations
search_chats- Search chats by topic or member namecreate_chat- Create new 1:1 or group chats
Message Operations
get_chat_messages- Retrieve messages from a specific chatsend_chat_message- Send messages with Markdown and mentionssearch_messages- Search across all Teams messages using KQL
💡 Example Queries
- "Search for chats with John Smith"
- "Show me recent messages from the Engineering chat"
- "Send a message to the Dev Team chat saying the deployment is complete"
- "Search all Teams messages mentioning the Q4 roadmap"
- "Create a group chat with Alice, Bob, and Carol about the new project"
- "Find all urgent messages from last week"
- "Get my user profile information"
🏗️ Development
From Source
# Clone and setup
git clone https://github.com/evrimalacan/mcp-microsoft-graph.git
cd mcp-microsoft-graph
npm install
# Set up credentials
cp .env.example .env.local
# Edit .env.local with your CLIENT_ID and TENANT_ID
# Build
npm run build
# Authenticate
npm run auth
# Development mode
npm run dev
# Run tests
npm test
Adding New Tools
- Create a new tool file in the appropriate domain folder under
src/tools/ - Export it from the domain's
index.ts - Register it in
src/tools/index.ts
See the existing tools for examples and patterns.
🐛 Troubleshooting
Common Issues
"Authentication failed"
- Run
npm run authto authenticate again - Verify your CLIENT_ID and TENANT_ID are correct
- Check that your Azure AD app has the required permissions
"Access forbidden"
- Ensure your Azure AD app has the necessary permissions granted
- Check if admin consent is required and has been granted
- Verify you're signed in with the correct account
"Token expired"
- Run
npm run authto refresh your authentication - Check that the token file path is accessible
"Chat not found"
- Verify the chat ID is correct
- Ensure you have access to the chat
- Check that the chat still exists
📚 Documentation
- Microsoft Graph Explorer - Interactive API testing
- Microsoft Graph Documentation - Official API reference
- Model Context Protocol - MCP specification
🤝 Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Add tests for your changes
- Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
MIT License - see LICENSE file for details.
🌟 Support
- 🐛 Bug Reports: GitHub Issues
- 💡 Feature Requests: GitHub Discussions
Built for seamless Microsoft Teams integration with AI assistants
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.