🚀 Unleash the Power of LLMs with MCP Teams Server: Seamless Integration for Microsoft Teams

The Model Context Protocol (MCP) revolutionizes how Large Language Model (LLM) applications interact with external data sources and tools. The MCP Teams Server is a powerful implementation of the MCP, designed to seamlessly integrate with Microsoft Teams, unlocking a new realm of possibilities for AI-driven workflows.

✨ Key Features

This integration empowers you to:

Initiate Engaging Threads: Start new conversations in Teams channels with compelling titles and content, effortlessly mentioning relevant users.
Dynamic Thread Updates: Enrich existing discussions by adding message replies, ensuring the right people are notified with user mentions.
Comprehensive Thread Insights: Retrieve and analyze complete thread replies for deeper understanding and context.
Effortless User Discovery: Easily list all members within a Teams channel for streamlined collaboration.
Real-time Message Access: Read channel messages to stay informed and leverage data for AI-driven insights.

🛠️ Prerequisites

Before you begin, ensure you have the following:

uv Package Manager: A modern and fast package installer.
Python 3.10+: The foundation for the server.
Microsoft Teams Account: With the necessary configurations.

⚙️ Installation

Get started in a few simple steps:

Clone the Repository:

git clone [repository-url]
cd mcp-teams-server

Create a Virtual Environment and Install Dependencies:
```
uv venv
uv sync --frozen --all-extras --dev
```

🏢 Microsoft Teams Configuration

Refer to the comprehensive MS Teams Setup Guide for detailed instructions on configuring Microsoft Teams and the required Azure resources.

🚀 Usage

Configure the following environment variables. You can use the sample file as a template:

Key	Description
TEAMS_APP_ID	UUID for your MS Entra ID application ID
TEAMS_APP_PASSWORD	Client secret
TEAMS_APP_TYPE	SingleTenant or MultiTenant
TEAMS_APP_TENANT_ID	Tenant uuid in case of SingleTenant
TEAM_ID	MS Teams Group Id or Team Id
TEAMS_CHANNEL_ID	MS Teams Channel ID with url escaped chars

Start the server:

uv run mcp-teams-server

💻 Development

For integration tests, set up these environment variables:

Key	Description
TEST_THREAD_ID	timestamp of the thread id
TEST_MESSAGE_ID	timestamp of the message id
TEST_USER_NAME	test user name

Run integration tests:

uv run pytest -m integration

🐳 Docker Support

Pre-built Image

A pre-built Docker image is available on ghcr.io:

docker pull ghcr.io/inditextech/mcp-teams-server:latest

Build Your Own Image

Build the Docker image with:

docker build . -t inditextech/mcp-teams-server

Run the Docker Image

Basic run:

docker run -it inditextech/mcp-teams-server

Run with environment variables from .env:

docker run --env-file .env -it inditextech/mcp-teams-server

🤖 LLM Integration

Follow the instructions in the LLM Installation Guide to set up your LLM to use the MCP Teams Server.

📜 Changelog

Stay up-to-date with the latest changes and version history in CHANGELOG.md.

🤝 Contributing

We welcome contributions! Please review CONTRIBUTING.md for our code of conduct and submission process.

🔒 Security

For security concerns, please consult our Security Policy.

mcp-teams-server