InditexTech/mcp-teams-server

What it solves

It enables Large Language Models (LLMs) to interact directly with Microsoft Teams, allowing AI agents to read and write messages, manage threads, and interact with team members without manual human intervention.

How it works

The project implements a server based on the Model Context Protocol (MCP), which acts as a standardized bridge between an LLM and the Microsoft Teams API. It supports multiple transport methods, including stdio, streamable-http, and sse, to facilitate communication between the AI client and the Teams environment.

Who it’s for

Developers building AI agents or LLM-powered workflows that need to automate communication, notifications, or information retrieval within Microsoft Teams channels.

Highlights

• Comprehensive Messaging: Ability to start new threads with titles, reply to existing threads, and read message histories.
• Member Management: Capability to list channel team members and mention specific users in messages.
• Flexible Deployment: Supports running via Python (using the uv package manager) or as a pre-built Docker image.
• Multiple Transports: Offers various communication protocols to ensure compatibility with different LLM clients.