Question 1

What is the Model Context Protocol (MCP)?

Accepted Answer

MCP is an open protocol standardizing how applications provide context to Large Language Models (LLMs), enabling AI models to access and interact with external data sources and tools in a consistent manner.

Question 2

What does the Teams Messenger MCP App do?

Accepted Answer

It bridges Microsoft Teams with MCP-compatible clients (LLMs, agentic frameworks) using a pure MCP server, allowing AI functionalities within Teams without requiring REST API endpoints.

Question 3

What are the key features of this MCP App?

Accepted Answer

Key features include Microsoft Teams chat integration, PostgreSQL-based Information Retrieval (IR) server, persistent storage in DuckDB, hybrid semantic/lexical search, a CLI for token management, and live event streaming for messages.

Question 4

What is the architecture of the Teams Messenger MCP App?

Accepted Answer

It connects Microsoft Teams to an MCP Server (Python, FastMCP), which interacts with a DuckDB database for storage and an IR Server (PostgreSQL) for advanced search.

Question 5

What are the installation requirements?

Accepted Answer

Requirements include Python 3.9+, pip, and Docker/Docker Compose for containerized deployment. Local installation is also possible.

Question 6

What environment variables need to be configured?

Accepted Answer

Required variables include Azure AD credentials (client ID, secret, tenant ID, app object ID), database paths (DuckDB and token), polling interval, and PostgreSQL/IR server settings.

Question 7

How do I run the MCP server locally?

Accepted Answer

After installing dependencies and configuring environment variables, run `python mcp_server/server.py`.

Question 8

How do I use the CLI client?

Accepted Answer

Use the CLI to login, list chats, get messages, send messages, create chats, search messages (hybrid, BM25, vector), and stream new messages.

Question 9

What search capabilities does the IR server provide?

Accepted Answer

The IR server offers advanced search using PostgreSQL and pgvector, including hybrid (BM25 + vector) search with LLM reranking.

Question 10

Can I test the app without real Teams API calls?

Accepted Answer

Yes, set `DEMO_MODE=true` in your `.env` file to use mock/demo mode.

Question 11

What is UBOS and how does it enhance this MCP App?

Accepted Answer

UBOS is a full-stack AI Agent Development Platform that helps you orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems. It provides a more comprehensive environment for AI agent development and management compared to the standalone MCP App.

Teams Messenger Integration Server

Resources

Project Details

Recomended MCP Servers

Featured Templates

Speech to Text

Customer Relationship Management (CRM)

AI-Powered Product List Manager

AI Chat Bot: Text, Voice, and Video Magic

Image to text with Claude 3

Unified Authorization Template

Start your free trial