Ckreiling MCP Server Docker

🐋 Docker MCP Server

A Natural Language Console Process (MCP) server for managing Docker!

This project offers a natural language interface to interact with Docker, enabling users to perform various Docker - related operations without writing complex commands.

🚀 Quick Start

Prerequisites

• Make sure uv is installed (refer to Documentation for details).
• Clone this repository.

Installation

Claude Desktop

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

"mcpServers": {
  "mcp-server-docker": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/repo",
      "run",
      "mcp-server-docker"
    ]
  }
}

✨ Features

• 🚀 Orchestrate containers using natural language.
• 🔍 Check and debug running containers.
• 📀 Manage persistent data using Docker volumes.

💁‍♂️ Who Is This For?

• Server administrators: Connect to a remote Docker engine, for example, to manage a publicly - facing website.
• Enthusiasts: Start containers locally without having to run any commands themselves.

💻 Usage Examples

🎻 docker_compose

Orchestrate containers using natural language.

Provide a project name and a description of the required containers, and let the Large Language Model (LLM) handle the rest.

This prompt instructs the LLM to enter a plan+apply cycle. Interactions with the LLM will involve the following steps:

1. You send instructions to the LLM indicating which containers to start.
2. The LLM calculates a concise natural - language plan and presents it to you.
3. You can:
   • Apply the plan.
   • Provide feedback to the LLM, and the LLM recalculates the plan.

Examples

• Name: nginx, Container: "Deploy an nginx container exposed on port 9000".
• Name: wordpress, Container: "Deploy a WordPress container and a supporting MySQL container, and expose WordPress on port 9000".

Resume a Project

When you start a new chat, the LLM will receive the status of any containers, volumes, and networks created with the given names.

This is mainly used for cleanup if you lose a chat that was responsible for many containers.

📚 Documentation

Resources

The server implements several resources for each container:

• Statistics: Container information such as CPU, memory, etc.
• Logs: View the tail of the container logs.

Tools

Containers

• list_containers
• create_container
• run_container
• recreate_container
• start_container
• fetch_container_logs
• stop_container
• remove_container

Images

• list_images
• pull_image
• push_image
• build_image
• remove_image

Networks

• list_networks
• create_network
• delete_network
• connect_container_to_network
• disconnect_container_from_network

Volumes

• list_volumes
• inspect_volume
• remove_volume

🚫 Disclaimer

This project is intended to provide users with an experimental natural - language interface to interact with Docker. It may not be suitable for production environments, and the functionality may change.

⚠️ Important Note

• Back up important data before use.
• Ensure you understand the potential impacts of all commands.
• Be careful when using it on a public network.