A powerful Model Context Protocol (MCP) server for Docker operations, enabling seamless container and compose stack management through Claude AI.

• 🚀 Container creation and instantiation
• 📦 Docker Compose stack deployment
• 🔍 Container logs retrieval
• 📊 Container listing and status monitoring

To try this in Claude Desktop app, add this to your claude config files:

{
  "mcpServers": {
    "docker-mcp": {
      "command": "uvx",
      "args": [
        "docker-mcp"
      ]
    }
  }
}

To install Docker MCP for Claude Desktop automatically via Smithery:

npx @smithery/cli install docker-mcp --client claude

• UV (package manager)
• Python 3.12+
• Docker Desktop or Docker Engine
• Claude Desktop

Add the server configuration to your Claude Desktop config file:

MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "docker-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "<path-to-docker-mcp>",
        "run",
        "docker-mcp"
      ]
    }
  }
}

{
  "mcpServers": {
    "docker-mcp": {
      "command": "uvx",
      "args": [
        "docker-mcp"
      ]
    }
  }
}

1. Clone the repository:

git clone https://github.com/QuantGeekDev/docker-mcp.git
cd docker-mcp

2. Create and activate a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies:

uv sync

Launch the MCP Inspector for debugging:

npx @modelcontextprotocol/inspector uv --directory <path-to-docker-mcp> run docker-mcp

The Inspector will provide a URL to access the debugging interface.

The server provides the following tools:

Creates a standalone Docker container

{
    "image": "image-name",
    "name": "container-name",
    "ports": {"80": "80"},
    "environment": {"ENV_VAR": "value"}
}

Deploys a Docker Compose stack

{
    "project_name": "example-stack",
    "compose_yaml": "version: '3.8'\nservices:\n  service1:\n    image: image1:latest\n    ports:\n      - '8080:80'"
}

Retrieves logs from a specific container

{
    "container_name": "my-container"
}

Lists all Docker containers

{}

• No built-in environment variable support for containers
• No volume management
• No network management
• No container health checks
• No container restart policies
• No container resource limits

1. Fork the repository from docker-mcp
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Alex Andru - Initial work | Core contributor - @QuantGeekDev
• Ali Sadykov - Initial work | Core contributor - @md-archive

Made with ❤️