Microsoft Teams MCP
Interact with Microsoft Teams to read, create, and reply to messages, and mention members.
MCP Teams Server
An MCP (Model Context Protocol) server implementation for Microsoft Teams integration, providing capabilities to read messages, create messages, reply to messages, mention members.
Features
https://github.com/user-attachments/assets/548a9768-1119-4a2d-bd5c-6b41069fc522
- Start thread in channel with title and contents, mentioning users
- Update existing threads with message replies, mentioning users
- Read thread replies
- List channel team members
- Read channel messages
Prerequisites
- uv package manager
- Python 3.10
- Microsoft Teams account with proper set-up
Installation
- 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
Teams configuration
Please read this document to help you to configure Microsoft Teams and required Azure resources. It is not a step-by-step guide but can help you figure out what you will need.
Usage
Set up the following environment variables in your shell or in an .env file. You can use 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
Integration tests require the set-up the following 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 |
uv run pytest -m integration
Pre-built docker image
There is a pre-built image hosted in ghcr.io. You can install this image by running the following command
docker pull ghcr.io/inditextech/mcp-teams-server:latest
Build docker image
A docker image is available to run MCP server. You can build it with the following command:
docker build . -t inditextech/mcp-teams-server
Run docker image
Basic run configuration:
docker run -it inditextech/mcp-teams-server
Run with environment variables from .env file:
docker run --env-file .env -it inditextech/mcp-teams-server
Setup LLM to use MCP Teams Server
Please follow instructions on the following document
Changelog
See CHANGELOG.md for a list of changes and version history.
Contributing
Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
Security
For security concerns, please see our Security Policy.
License
This project is licensed under the Apache-2.0 file for details.
© 2025 INDUSTRIA DE DISEÑO TEXTIL S.A. (INDITEX S.A.)
Servidores relacionados
mcp2mqtt
An MCP service for device communication and PWM control via the MQTT protocol.
Slack
Interact with Slack workspaces to read and send messages directly through your AI assistant.
Aura Backend - Advanced AI Companion
An advanced AI companion with emotional intelligence and vector database integration.
Teams MCP
Interact with Microsoft Teams, users, and organizational data via the Microsoft Graph API.
Email
This server enables users to send emails through various email providers, including Gmail, Outlook, Yahoo, Sina, Sohu, 126, 163, and QQ Mail. It also supports attaching files from specified directories, making it easy to upload attachments along with the email content.
BlueSky
Access the BlueSky social network data via its official API.
Voyp
Integrate AI assistants with VOYP's calling capabilities to make calls, search business info, and manage call status.
RSS MCP Server by CData
A read-only MCP server for querying live RSS data using the CData JDBC Driver for RSS.
messages
Fuzzy search and browse Apple Messages/iMessage from CLI or MCP server
Phone-a-Friend MCP Server
An AI-to-AI consultation system for complex problem-solving and reasoning, using OpenRouter for model access.