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.

python

356

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "inditextech-mcp-teams-server": {
      "command": "uv",
      "args": [
        "run",
        "mcp-teams-server"
      ],
      "env": {
        "TEAM_ID": "YOUR_TEAM_ID",
        "TEAMS_APP_ID": "YOUR_APP_ID",
        "TEAMS_APP_TYPE": "SingleTenant|MultiTenant",
        "TEAMS_CHANNEL_ID": "YOUR_CHANNEL_ID",
        "TEAMS_APP_PASSWORD": "YOUR_APP_PASSWORD",
        "TEAMS_APP_TENANT_ID": "YOUR_TENANT_ID"
      }
    }
  }
}

You can run an MCP server that integrates with Microsoft Teams to read messages, post new messages, reply in threads, and mention members. This server acts as a bridge between your Teams channels and the MCP ecosystem, letting you automate conversations and manage channel activity from your MCP client.

How to use

Use an MCP client to connect to the Teams MCP server and perform actions like starting a thread in a channel, posting messages, replying to messages, and mentioning users. You can read thread replies, list channel members, and fetch channel messages to build workflows, bots, or automation that interacts with your Teams space.

How to install

Prerequisites: Python 3.10, uv package manager, and a Microsoft Teams account with the required setup.

Step by step install and run sequence:

uv venv
uv sync --frozen --all-extras --dev

Configure and run

Set up environment variables in your shell or in an .env file. The MCP server uses the following variables to connect to Teams and identify your application.

Required environment variables:

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 with the following command.

uv run mcp-teams-server

Development

If you want to run integration tests locally, set up the following test environment variables and run the test suite.

Environment variables for tests:

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

Docker usage

There are pre-built and buildable Docker images available for running the MCP Teams server. Use these commands to pull, build, and run the container.

Pull the pre-built image (if available):

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

Build your own image from the repository root:

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

Run the image with optional environment variables from a .env file:

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

Configuration notes

The server expects Microsoft Teams related credentials and identifiers to connect and operate. Ensure your Teams app registration includes the correct permissions and that the encoded channel and team identifiers are provided as environment variables.

Available tools

readThread

Read replies in a thread in a channel to fetch context for automation.

createMessage

Create a new message in a channel thread, optionally mentioning members.

replyMessage

Post a reply to an existing message within a thread.

mentionMember

Mention a member in a channel message to draw attention to a participant.

listMembers

List members of the specified channel team.

readMessages

Read messages in a channel to surface recent activity.

Built by

VeilStrat

AI signals for GTM teams