ChatGPT MCP Server

What is ChatGPT MCP Server?

The ChatGPT MCP Server is a Model Context Protocol (MCP) server that provides Docker management capabilities through a custom GPT interface. It allows users to interact with Docker containers using natural language, built with TypeScript and designed for containerized deployment.

How to use ChatGPT MCP Server?

Install via Smithery with npx -y @smithery/cli install @Toowiredd/chatgpt-mcp-server --client claude or manually: clone the repo, install dependencies, create an .env file, build with npm run build, and run with Docker using npm run docker:run or manually with docker run. Set environment variables like API_KEY for authentication.

Key features of ChatGPT MCP Server

• Docker container management through natural language
• Built on the Model Context Protocol (MCP)
• TypeScript implementation with robust error handling
• Containerized deployment with graceful shutdown
• Rate limiting and API key authentication
• Resource management and port conflict detection

Use cases of ChatGPT MCP Server

• Manage Docker containers via natural language commands in a custom GPT
• Automate container lifecycles (start, stop, monitor) without CLI
• Integrate Docker operations into ChatGPT-based workflows

FAQ from ChatGPT MCP Server

What exactly does the ChatGPT MCP Server do?

It provides Docker management capabilities, allowing users to control Docker containers through natural language via a custom GPT interface, using the Model Context Protocol.

How do I install the ChatGPT MCP Server?

Install automatically via Smithery with the command npx -y @smithery/cli install @Toowiredd/chatgpt-mcp-server --client claude, or manually by cloning the repository, installing dependencies, setting environment variables, and building with npm.

What runtime or dependencies are required?

The server requires Node.js and Docker. It runs inside a Docker container and mounts the host’s Docker socket (/var/run/docker.sock) to interact with Docker.

What environment variables are needed?

Key variables: API_KEY for authentication, HTTP_PORT (default 3001), RATE_LIMIT_REQUESTS, and RATE_LIMIT_WINDOW for rate limiting.

How does the server handle shutdown and errors?

It performs a graceful shutdown on SIGINT, SIGTERM, and SIGQUIT: rejects new connections, allows active requests to complete (with timeout), closes keep-alive connections, releases ports, and cleans up resources. Port conflicts, unhandled rejections, and network errors are properly caught.