Mcp Teams

v1.0.0Communicationstable

An MCP (Model Context Protocol) server implementation for Microsoft Teams integration, providing capabilities to read messages, create messages, reply to messages, mention members.

inditexmcpmcp-servermsteams
Share:
373
Stars
0
Downloads
0
Weekly
0/5

What is Mcp Teams?

Mcp Teams is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp (model context protocol) server implementation for microsoft teams integration, providing capabilities to read messages, create messages, reply to messages, mention members.

An MCP (Model Context Protocol) server implementation for Microsoft Teams integration, providing capabilities to read messages, create messages, reply to messages, mention members.

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP (Model Context Protocol) server implementation for Mi

Use Cases

Read and write Microsoft Teams messages.
Manage team communications.
Mention members and reply to threads.
InditexTech

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 13, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-teams

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Mcp Teams

The mcp-teams MCP server is a Python-based Microsoft Teams integration developed by InditexTech that lets AI agents read channel messages, create conversation threads, post replies, and mention specific team members — all through the Model Context Protocol. It connects to Teams via an Azure Bot Framework application registered in Microsoft Entra ID, supporting both SingleTenant and MultiTenant deployments. This is well-suited for enterprise automation scenarios such as AI-driven incident management, automated daily standups posted to a channel, or AI assistants that monitor and respond to Teams messages on behalf of a team.

Prerequisites

  • Python 3.10 and uv package manager installed
  • A Microsoft Azure account with permission to register an Entra ID application and grant Teams API permissions
  • A Microsoft Teams account with access to the target team and channel
  • Your Team ID and URL-encoded Channel ID from the Teams admin console or Microsoft Graph Explorer
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Register an Azure Entra ID application

In Azure Portal, create a new App Registration. Note the Application ID, create a client secret, and grant Microsoft Graph permissions including ChannelMessage.Read.All, ChannelMessage.Send, and TeamMember.Read.All. Have an admin grant consent.

2

Clone the repository and install dependencies

Clone the InditexTech mcp-teams-server repository and set up the Python environment with uv.

git clone https://github.com/InditexTech/mcp-teams-server.git
cd mcp-teams-server
uv venv && uv sync --frozen --all-extras --dev
3

Configure credentials in a .env file

Create a .env file in the project root with your Azure app credentials and Teams identifiers. TEAMS_CHANNEL_ID must be URL-encoded.

TEAMS_APP_ID=your-entra-app-uuid
TEAMS_APP_PASSWORD=your-client-secret
TEAMS_APP_TYPE=SingleTenant
TEAMS_APP_TENANT_ID=your-tenant-uuid
TEAM_ID=your-teams-group-id
TEAMS_CHANNEL_ID=your-url-encoded-channel-id
4

Start the server

Run the MCP server. It will load credentials from the .env file and start accepting MCP connections.

uv run mcp-teams-server
5

Or run via Docker

Use the GitHub Container Registry image if you prefer not to manage a Python environment.

docker pull ghcr.io/inditextech/mcp-teams-server:latest
docker run --env-file .env -it ghcr.io/inditextech/mcp-teams-server:latest

Mcp Teams Examples

Client configuration

Claude Desktop configuration for the mcp-teams server running via uv. All six environment variables are required for the server to authenticate and connect to your Teams channel.

{
  "mcpServers": {
    "mcp-teams": {
      "command": "uv",
      "args": ["run", "mcp-teams-server"],
      "env": {
        "TEAMS_APP_ID": "your-entra-app-uuid",
        "TEAMS_APP_PASSWORD": "your-client-secret",
        "TEAMS_APP_TYPE": "SingleTenant",
        "TEAMS_APP_TENANT_ID": "your-tenant-uuid",
        "TEAM_ID": "your-teams-group-id",
        "TEAMS_CHANNEL_ID": "your-url-encoded-channel-id"
      }
    }
  }
}

Prompts to try

Example tasks for your AI agent working with Microsoft Teams through the mcp-teams server.

- "Read the most recent messages in the channel and summarize them"
- "Create a thread titled 'Weekly Sync Notes' and post this week's action items"
- "Reply to the last message in the channel and mention @jane.smith"
- "Who are the members of this team?"
- "Post a message to the channel announcing that the deployment to production succeeded"

Troubleshooting Mcp Teams

Authentication returns 401 or 403 errors

Check that TEAMS_APP_ID and TEAMS_APP_PASSWORD are correct and that the client secret has not expired in Azure Portal. For SingleTenant apps, ensure TEAMS_APP_TENANT_ID is the correct directory (tenant) UUID, not the object ID.

Cannot find the channel or messages return empty

TEAMS_CHANNEL_ID must be URL-encoded. Retrieve it from the Microsoft Graph Explorer (https://developer.microsoft.com/graph/graph-explorer) by calling GET /teams/{team-id}/channels, then URL-encode the ID value before putting it in your .env file.

uv run mcp-teams-server fails with import errors

Run 'uv sync --frozen --all-extras --dev' again to ensure all dependencies are installed. If the error persists, delete the .venv directory and re-run 'uv venv && uv sync --frozen --all-extras --dev'.

Frequently Asked Questions about Mcp Teams

What is Mcp Teams?

Mcp Teams is a Model Context Protocol (MCP) server that mcp (model context protocol) server implementation for microsoft teams integration, providing capabilities to read messages, create messages, reply to messages, mention members. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Mcp Teams?

Follow the installation instructions on the Mcp Teams GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Mcp Teams?

Mcp Teams works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Mcp Teams free to use?

Yes, Mcp Teams is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-teams": { "command": "npx", "args": ["-y", "mcp-teams"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Mcp Teams?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides