Microsoft 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:
374
Stars
0
Downloads
0
Weekly
0/5

What is Microsoft Teams?

Microsoft 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 create Teams messages.
Reply to messages and mention members.
Automate team communications.
InditexTech

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-microsoft-teams-server

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 Microsoft Teams

The MCP Microsoft Teams Server is a Python-based MCP integration built by InditexTech that connects AI agents to Microsoft Teams, enabling them to read channel messages, create new threads, post replies, and mention team members programmatically through a structured MCP interface. It authenticates via Azure's Bot Framework using an Entra ID application, making it suitable for enterprise deployments where Teams is the primary communication platform. This server allows AI coding assistants and automation agents to participate in or monitor Teams channels without a human in the loop, useful for automated reporting, incident notification, or knowledge-base queries surfaced directly in Teams.

Prerequisites

  • Python 3.10 and uv package manager installed
  • A Microsoft Azure account with permission to register an Entra ID (Azure AD) application
  • A Microsoft Teams account with access to the target team and channel
  • The target Team ID and Channel ID from your Teams environment
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Register an Azure Bot / Entra ID application

In the Azure Portal, create an App Registration under Microsoft Entra ID. Note the Application (client) ID and create a client secret. Configure the bot as SingleTenant or MultiTenant and grant the required Microsoft Graph and Teams permissions.

2

Clone the repository and install dependencies

Clone the mcp-teams-server repository and install Python dependencies using uv.

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

Create a .env file with your credentials

Copy the sample .env file and fill in your Azure application credentials and Teams channel identifiers.

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-channel-id-url-encoded
4

Start the MCP server

Run the server using uv. It will read credentials from the .env file and start listening for MCP connections.

uv run mcp-teams-server
5

Or deploy with Docker

Use the pre-built Docker image from GitHub Container Registry for a self-contained deployment without Python setup.

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

Microsoft Teams Examples

Client configuration

Claude Desktop configuration for the Microsoft Teams MCP server. The env block must contain all required Azure and Teams credentials.

{
  "mcpServers": {
    "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 you can ask your AI agent to perform in Microsoft Teams once the server is connected.

- "Read the last 10 messages from the general channel"
- "Create a new thread in the channel with the title 'Deploy update v2.4' and summarize the changes"
- "Reply to the latest thread and mention @john.doe"
- "List all members of the team"
- "Post a status update to the channel saying the nightly build completed successfully"

Troubleshooting Microsoft Teams

Authentication fails with 401 Unauthorized

Verify that TEAMS_APP_ID and TEAMS_APP_PASSWORD match your Azure App Registration exactly. If using SingleTenant, confirm TEAMS_APP_TENANT_ID is the correct tenant UUID. Ensure the client secret has not expired in the Azure Portal.

TEAMS_CHANNEL_ID is not found or returns 404

The channel ID must be URL-encoded because Teams channel IDs contain special characters. Copy the channel ID from the Teams web URL and URL-encode it, or use the Microsoft Graph Explorer to retrieve the correct encoded ID.

Server starts but no messages can be read from the channel

Ensure the Azure app has been granted and admin-consented the required Microsoft Graph API permissions (ChannelMessage.Read.All, ChannelMessage.Send, TeamMember.Read.All). Check the Azure Portal under API permissions for your app registration.

Frequently Asked Questions about Microsoft Teams

What is Microsoft Teams?

Microsoft 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 Microsoft Teams?

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

Which AI clients work with Microsoft Teams?

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

Is Microsoft Teams free to use?

Yes, Microsoft 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-microsoft-teams-server": { "command": "npx", "args": ["-y", "mcp-microsoft-teams-server"] } } }

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

Read the full setup guide →

Ready to use Microsoft 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