Chat MCP

What is chat-mcp

chat-mcp is an asynchronous API server developed by karthikv2k using FastAPI that facilitates communication with Model Context Protocol (MCP) servers. This server acts as an intermediary, allowing users to interact seamlessly with MCP servers. MCP is a protocol designed to securely connect AI systems with various data sources and tools, providing a standardized way for AI assistants to access and utilize external information.

How to Use chat-mcp

To use chat-mcp, you need to have Python 3.8 or higher installed and access to an MCP server, either locally or remotely. Begin by cloning the chat-mcp repository to your local system and setting up a virtual environment. After installing the required dependencies, configure your MCP server details in the .env file. Once everything is set up, you can start the server using Uvicorn, a lightning-fast ASGI server for Python.

After the server is running, you can interact with it using API endpoints. These endpoints allow you to list available MCP servers, view tools provided by these servers, and invoke specific tools. The server runs locally by default at http://localhost:8000, where you can also access an interactive API documentation interface.

Key Features of chat-mcp

• List Available MCP Servers: This feature enables users to discover all accessible MCP servers that can be connected to the chat-mcp server. This is done through the POST /api/list-mcp-servers endpoint, which provides a comprehensive list of servers available for interaction.

• List Tools from MCP Servers: With the POST /api/list-tools endpoint, users can retrieve a list of tools that an MCP server offers. This is crucial for understanding the capabilities and resources available on a particular server.

• Invoke Tools on MCP Servers: The POST /api/invoke-tool endpoint allows users to execute specific tools on an MCP server. By providing the server URL, tool name, and necessary parameters, users can perform desired operations or retrieve specific data.

Each of these features is designed to make the interaction with MCP servers intuitive and efficient, catering to both technical and non-technical users. Whether you need to access real-time data or utilize advanced AI tools, chat-mcp provides a streamlined and secure way to bridge the gap between AI clients and rich data sources.