Docker MCP Server

A powerful Model Context Protocol (MCP) server that executes code in isolated Docker containers and returns the results to language models like Claude.

Features

• Isolated Code Execution: Run code in Docker containers separated from your main system
• Multi-language Support: Execute code in any language with a Docker image
• Complex Script Support: Run both simple commands and complete multi-line scripts
• Package Management: Install dependencies using pip, npm, apt-get, or apk
• Container Management: Create, list, and clean up Docker containers easily
• Robust Error Handling: Graceful timeout management and fallback mechanisms
• Colorful Output: Clear, color-coded console feedback

Requirements

• Python 3.9+
• Docker installed and running
• fastmcp library

Installation

1. Clone this repository:

   git clone https://github.com/zaycruz/docker_mcp.git
   cd docker_mcp
   

2. Create a virtual environment:

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

3. Install required packages:

   pip install -r requirements.txt
   

Usage

Running the MCP Inspector

To test and explore the server’s functionality:

python run_server.py

The MCP Inspector interface will open in your browser at http://localhost:5173.

Available Tools

The Docker MCP server provides the following tools:

1. List Containers

Lists all Docker containers and their details:

• Parameters:
  • show_all: (Optional) Whether to show all containers including stopped ones (default: True)

2. Create Container

Creates and starts a Docker container with optional dependencies:

• Parameters:
  • image: The Docker image to use (e.g., “python:3.9-slim”, “node:16”)
  • container_name: A unique name for the container
  • dependencies: (Optional) Space-separated list of packages to install (e.g., “numpy pandas”, “express lodash”)

3. Add Dependencies

Installs additional packages in an existing Docker container:

• Parameters:
  • container_name: The name of the target container
  • dependencies: Space-separated list of packages to install

4. Execute Code

Executes a command inside a running Docker container:

• Parameters:
  • container_name: The name of the target container
  • command: The command to execute inside the container

5. Execute Python Script

Executes a multi-line Python script inside a running Docker container:

• Parameters:
  • container_name: The name of the target container
  • script_content: The full Python script content
  • script_args: Optional arguments to pass to the script

6. Cleanup Container

Stops and removes a Docker container:

• Parameters:
  • container_name: The name of the container to clean up

Examples

Basic Workflow Example

# 1. List existing containers to see what's already running