Skip to main content
Glama

Teams Messenger MCP App

by aech-ai

Teams Messenger MCP App

This project implements a pure Model Context Protocol (MCP) server that bridges Microsoft Teams and MCP-compatible clients (LLMs, agentic frameworks, and a rich CLI MCP client). All features are exposed via MCP tools, resources, and events—no REST API endpoints.

Features

  • Microsoft Teams chat/message integration via MCP
  • PostgreSQL-based Information Retrieval (IR) server for advanced search capabilities
  • Persistent storage in DuckDB for chat/message history
  • Hybrid semantic and lexical search (BM25 + vector, FlockMTL-style)
  • CLI for login/token management and a rich MCP client for local testing
  • Polling-based event emission for new messages
  • Live event streaming and search for LLMs and CLI
  • Single-agent (bot) account, not multi-user

Architecture

+-------------------+ +-------------------+ +-------------------+ | CLI MCP Client |<---->| MCP Server |<---->| Microsoft Teams | | (rich terminal UI)| | (Python, FastMCP) | | (Graph API) | +-------------------+ +-------------------+ +-------------------+ | | | v | +-------------------+ +-------------------+ | | DuckDB DB | | IR Server | | +-------------------+ | (PostgreSQL, API) | +-------------------+ | v +-------------------+ | PostgreSQL DB | | (with pgvector) | +-------------------+
  • All chat/message/search logic is via MCP tools/resources/events
  • Teams MCP server uses DuckDB for message storage
  • IR server provides advanced search capabilities with PostgreSQL and pgvector
  • IR server exposes an HTTP API for MCP server communication

Installation

Requirements

Option 1: Local Installation

1. Clone the repository
git clone <your-repo-url> cd mcp-teams
2. Install dependencies
pip install -r requirements.txt
3. Configure environment variables

Copy the template and fill in your Azure AD/Teams credentials:

cp .env.template .env # Edit .env and fill in your Azure AD and other settings

See the table below for variable descriptions.

1. Clone the repository
git clone <your-repo-url> cd mcp-teams
2. Configure environment variables

Copy the template and fill in your credentials:

cp .env.template .env # Edit .env and fill in your settings
3. Build and start services
docker-compose up -d

Environment Variables (.env)

VariableDescriptionExample / Default
AZURE_CLIENT_IDAzure AD Application (client) IDxxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
AZURE_CLIENT_SECRETAzure AD Application secretyour-secret
AZURE_TENANT_IDAzure AD Tenant IDxxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
AZURE_APP_OBJECT_IDAzure AD Application object IDxxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
DUCKDB_PATHPath to DuckDB database filedb/teams_mcp.duckdb
TOKEN_PATHPath to store persistent token cachedb/token_cache.json
POLL_INTERVALPolling interval (seconds) for new messages10
DEMO_MODESet to true for mock/demo mode (no real Teams API calls)false
OPENAI_API_KEYOpenAI API key for embedding generationsk-...
POSTGRES_USERPostgreSQL usernamepostgres
POSTGRES_PASSWORDPostgreSQL passwordpostgres
POSTGRES_DBPostgreSQL database namemcp_ir
IR_SERVER_HOSTIR server hostnameir_server
IR_SERVER_PORTIR server port8090

Running the MCP Server

Local Mode (without Docker)

python mcp_server/server.py

Docker Mode (All Services)

docker-compose up -d

To check logs:

docker-compose logs -f teams_mcp # Teams MCP server logs docker-compose logs -f ir_server # IR server logs

Demo Mode (no real Teams API calls)

Set DEMO_MODE=true in your .env and run as above.

CLI Usage

1. Login and Token Management

python cli/login.py login python cli/login.py status python cli/login.py logout

2. Rich CLI MCP Client

All commands below use the MCP stdio protocol to talk to the server.

List chats
python cli/mcp_client.py list_chats
Get messages from a chat
python cli/mcp_client.py get_messages <chat_id>
Send a message
python cli/mcp_client.py send_message <chat_id> "Hello from CLI!"
Create a new 1:1 chat
python cli/mcp_client.py create_chat <user_id_or_email>
Search messages (hybrid, BM25, or vector)
python cli/mcp_client.py search_messages "project update" --mode hybrid --top_k 5
Stream new incoming messages (live event subscription)
python cli/mcp_client.py stream

IR Server Usage

The IR server provides advanced search capabilities with PostgreSQL and pgvector. It exposes an HTTP API for MCP server communication.

IR Server API Endpoints

1. Health Check
GET http://localhost:8090/
2. List Available Tools
GET http://localhost:8090/api/tools
3. Search Content
POST http://localhost:8090/api/tools/search

Body:

{ "query": "your search query", "search_type": "hybrid", "limit": 10 }
4. Index Content
POST http://localhost:8090/api/tools/index_content

Body:

{ "content": "Text content to index", "source_type": "teams", "metadata": { "author": "User Name", "created": "2025-04-01T12:00:00Z" } }

For more detailed IR server documentation, see ir/README.md.

Search and Event Streaming

  • Hybrid search: Combines BM25 and vector search with LLM reranking
  • Live streaming: Subscribe to messages/incoming for real-time updates

Development & Extension

  • Add new MCP tools/resources in mcp_server/server.py
  • Extend Teams integration in teams/graph.py
  • Modify IR capabilities in the IR server
  • Add analytics, summarization, or RAG features using DuckDB, PostgreSQL, and LLMs
  • Use the CLI as a test harness for all MCP features

Troubleshooting & FAQ

  • Login fails: Check your Azure AD credentials and .env values
  • No messages appear: Ensure polling is running and your bot account is in the Teams chat
  • DuckDB errors: Check file permissions and paths in .env
  • IR server not responding: Check Docker logs and ensure the container is running
  • Demo mode: Set DEMO_MODE=true for local testing without real Teams

References


For full product details, see specs/app-spec.md.

-
security - not tested
F
license - not found
-
quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

A Model Context Protocol server that bridges Microsoft Teams with MCP-compatible clients (LLMs, agentic frameworks, CLI), enabling chat integration, message search, and event streaming without traditional REST API endpoints.

  1. Features
    1. Architecture
      1. Installation
        1. Requirements
        2. Option 1: Local Installation
        3. Option 2: Docker Deployment (Recommended)
      2. Environment Variables (.env)
        1. Running the MCP Server
          1. Local Mode (without Docker)
          2. Docker Mode (All Services)
          3. Demo Mode (no real Teams API calls)
        2. CLI Usage
          1. Login and Token Management
          2. Rich CLI MCP Client
        3. IR Server Usage
          1. IR Server API Endpoints
        4. Search and Event Streaming
          1. Development & Extension
            1. Troubleshooting & FAQ
              1. References

                Related MCP Servers

                • A
                  security
                  A
                  license
                  A
                  quality
                  An educational implementation of a Model Context Protocol server that demonstrates how to build a functional MCP server for integrating with various LLM clients like Claude Desktop.
                  Last updated -
                  1
                  88
                  Python
                  MIT License
                  • Apple
                  • Linux
                • A
                  security
                  A
                  license
                  A
                  quality
                  A Model Context Protocol server that enables interaction with Microsoft Dynamics 365 CRM from Claude Desktop, allowing users to retrieve, create, and update CRM data through natural language.
                  Last updated -
                  5
                  4
                  TypeScript
                  MIT License
                • -
                  security
                  A
                  license
                  -
                  quality
                  A demonstration server that implements the Model Context Protocol (MCP) SDK, providing tools and endpoints for server-sent events and message handling.
                  Last updated -
                  27
                  TypeScript
                  MIT License
                • -
                  security
                  -
                  license
                  -
                  quality
                  A Model Context Protocol server that bridges Microsoft Teams and MCP-compatible clients, enabling chat integration, message handling, and advanced search capabilities without REST API endpoints.
                  Last updated -
                  Python

                View all related MCP servers

                MCP directory API

                We provide all the information about MCP servers via our MCP API.

                curl -X GET 'https://glama.ai/api/mcp/v1/servers/aech-ai/mcp-teams'

                If you have feedback or need assistance with the MCP directory API, please join our Discord server