ChatGPT MCP Server

A Model Context Protocol (MCP) server that provides Docker management capabilities through a custom GPT interface.

Features

• Docker container management through natural language

• Built on the Model Context Protocol (MCP)

• TypeScript implementation

• Containerized deployment

• Robust error handling and graceful shutdown

• Resource management and port handling

• Rate limiting and API key authentication

Related MCP server: MCP Development Server

Setup

Installing via Smithery

To install ChatGPT MCP Server for Claude Desktop automatically via Smithery:

Manual Installation

1. Clone the repository

2. Install dependencies

3. Create environment file

4. Build the project

Running with Docker

1. Build the container

2. Run the container

Or manually:

Development

• npm run build - Build the TypeScript code

• npm run watch - Watch for changes and rebuild

• npm run inspector - Run the MCP inspector tool

Environment Variables

• API_KEY - API authentication key

• HTTP_PORT - Server port (default: 3001)

• RATE_LIMIT_REQUESTS - Maximum requests per window

• RATE_LIMIT_WINDOW - Window size in milliseconds

Resource Management

The server implements robust resource management:

• Graceful shutdown on process signals (SIGINT, SIGTERM, SIGQUIT)

• Connection tracking and management

• Request timeout handling

• Port conflict detection

• Keep-alive connection management

• Active request tracking and graceful completion

Shutdown Process

1. The server initiates graceful shutdown on process signals

2. New connections are rejected

3. Active requests are allowed to complete (with timeout)

4. Keep-alive connections are closed

5. Server ports are properly released

6. Resources are properly released

Error Handling

• Port conflicts are detected and reported

• Unhandled rejections and exceptions are caught

• Network errors are properly handled

• Resource leaks are prevented through proper handling

• Timeouts ensure the server doesn't hang during shutdown

License

MIT