mattermost-mcp-hostA Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based Agent.

A Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based AI agent to provide an intelligent interface for interacting with users and executing tools directly within Mattermost. This integration, which works as follows: Mattermost Connection (mattermost_client.py): Connects to the Mattermost server via API and WebSocket to listen for messages in a specified channel. MCP Connections (mcp_client.py): Establishes connections (primarily stdio) to each MCP server defined in src/mattermost_mcp_host/mcp-servers.json. It discovers available tools on each server. Agent Initialization (agent/llm_agent.py): A LangGraphAgent is created, configured with the chosen LLM provider and the dynamically loaded tools from all connected MCP servers. Message Handling (main.py): If a message starts with the command prefix (#), it's parsed as a direct command to list servers/tools or call a specific tool via the corresponding MCPClient. Otherwise, the message (along with thread history) is passed to the LangGraphAgent. The integration features a LangGraph Agent Integration, MCP Server Integration, Dynamic Tool Loading, Thread-Aware Conversations, Intelligent Tool Use, and MCP Capability Discovery. Direct command interface is also provided to interact directly with MCP servers using a command prefix. The integration uses a .env file for configuration, and can be installed using uv. The demo includes examples for searching issues and posting to a channel using Mattermost-MCP-server.