This repository provides an MCP server that connects a builder’s agent to Microsoft Teams. The server exposes tools for reading channel messages, creating new thread messages, replying to threads, listing team members, and mentioning people. It can run locally over stdio or be deployed over streamable HTTP.
Builders who want their agent to read and write Microsoft Teams messages.
You can keep work moving in Teams without switching out of your agent or copying messages by hand.
Lets the agent fetch messages from a channel thread.
Creates a new thread with a title and message content.
Posts replies to an existing thread.
Adds member mentions in new messages and replies.
Returns the members of a channel team.
Runs with stdio by default, or with streamable HTTP for server-style setups.
git clone https://github.com/InditexTech/mcp-teams-server cd mcp-teams-server
uv venv uv sync --frozen --all-extras --dev
uv run mcp-teams-server
uv run mcp-teams-server --transport streamable-http
An MCP (Model Context Protocol) server implementation for Microsoft Teams integration, providing capabilities to read messages, create messages, reply to messages, mention members.
https://github.com/user-attachments/assets/548a9768-1119-4a2d-bd5c-6b41069fc522
git clone https://github.com/InditexTech/mcp-teams-server
cd mcp-teams-server
uv venv
uv sync --frozen --all-extras --dev
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.
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_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
The default MCP transport is stdio. You can also use streamable-http for HTTP deployments:
uv run mcp-teams-server --transport streamable-http
The legacy sse transport is still available for older clients.
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
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
A docker image is available to run MCP server. You can build it with the following command:
docker build . -t inditextech/mcp-teams-server
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
Run with Streamable HTTP transport:
docker run --env-file .env -p 8000:8000 -it inditextech/mcp-teams-server --transport streamable-http
Please follow instructions on the following document
See CHANGELOG.md for a list of changes and version history.
Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.
For security concerns, please see our Security Policy.
This project is licensed under the Apache-2.0 file for details.
© 2025 INDUSTRIA DE DISEÑO TEXTIL S.A. (INDITEX S.A.)
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具，支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库，提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。