Skip to main content
Glama
ChatGPT MCP Server

ChatGPT MCP Server

by Toowiredd

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:

npx -y @smithery/cli install @Toowiredd/chatgpt-mcp-server --client claude

Manual Installation

  1. Clone the repository

git clone https://github.com/toowiredd/chatgpt-mcp-server.git
cd chatgpt-mcp-server
  1. Install dependencies

npm install
  1. Create environment file

cp env.example .env
# Edit .env with your configuration
  1. Build the project

npm run build

Running with Docker

  1. Build the container

npm run docker:build
  1. Run the container

npm run docker:run

Or manually:

docker run -d \
  -p 3001:3001 \
  --env-file .env \
  -v /var/run/docker.sock:/var/run/docker.sock \
  chatgpt-mcp-server

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

Available Tools

7 tools
container_createC

Create and start a new Docker container

Inputs: image (required), name, ports, env.

container_execC

Execute a command in a running container

Inputs: container (required), command (required).

container_logsC

Get container logs

Inputs: container (required), tail.

container_removeC

Remove a container

Inputs: container (required), force.

containers_listC

List all Docker containers

Inputs: all.

container_startC

Start a stopped container

Inputs: container (required).

container_stopC

Stop a running container

Inputs: container (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose targeting specific Docker container operations: create, execute, logs, remove, list, start, and stop. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.

    Naming Consistency5/5

    All tools follow a consistent 'container_verb' or 'containers_verb' pattern with snake_case, except for 'containers_list' which uses plural 'containers' for listing multiple items. This minor deviation is logical and maintains overall naming predictability across the set.

    Tool Count5/5

    With 7 tools, this server is well-scoped for Docker container management, covering essential lifecycle operations without being overly sparse or bloated. Each tool serves a clear and necessary function in the domain.

    Completeness5/5

    The tool set provides complete CRUD/lifecycle coverage for Docker containers: create, start, stop, execute commands, view logs, list, and remove. There are no obvious gaps, enabling agents to handle typical container workflows without dead ends.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers