Docker MCP

16 forks

122 stars

Free

What is docker-mcp

docker-mcp is a powerful Model Context Protocol (MCP) server developed by QuantGeekDev, designed for seamless Docker operations. It enables efficient management of Docker containers and Compose stacks, utilizing the capabilities of Claude AI to facilitate these tasks. By integrating with Claude, docker-mcp allows users to deploy and manage containerized applications easily, making it an invaluable tool for developers and system administrators who work with Docker environments.

How to Use docker-mcp

To get started with docker-mcp, you need to integrate it into your Claude Desktop application. This involves configuring your Claude Desktop settings to include docker-mcp as an MCP server. Here’s a quick guide on how to do that:

Prerequisites: Ensure you have the following installed:
- Python 3.12 or later
- Docker Desktop or Docker Engine
- Claude Desktop application
- UV package manager
Claude Desktop Configuration: Modify your Claude Desktop configuration file to recognize docker-mcp as an MCP server. Depending on your operating system, this file is located in different directories:
- MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%/Claude/claude_desktop_config.json
Installation via Command Line: You can use the Smithery CLI tool to install docker-mcp automatically for your Claude Desktop:
```
npx @smithery/cli install docker-mcp --client claude
```
Running docker-mcp: Once configured, you can start using docker-mcp to manage Docker containers and stacks directly from the Claude interface.

Key Features of docker-mcp

Container Creation and Management: Easily create and manage standalone Docker containers using simple commands. This includes specifying images, container names, ports, and environment variables.
Docker Compose Stack Deployment: Deploy complex multi-container applications using Docker Compose. This feature allows you to define your stack configuration in YAML format for streamlined deployment.
Log Retrieval: Fetch logs from specific containers to monitor application performance and troubleshoot issues effectively.
Container Listing and Status Monitoring: Quickly list all running containers and check their status, ensuring you have full visibility into your Docker environment at all times.

docker-mcp simplifies the process of managing Docker environments by leveraging the Model Context Protocol, providing an intuitive interface for users to interact with Docker through Claude AI. With its straightforward setup and robust feature set, docker-mcp is an essential tool for anyone looking to enhance their Docker management capabilities.

Python 3.12 License: MIT Code style: black A powerful Model Context Protocol (MCP) server for Docker operations, enabling seamless container and compose stack management through Claude AI.

✨ Features

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

🎬 Demos

Deploying a Docker Compose Stack

Analyzing Container Logs

🚀 Quickstart

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

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

Installing via

To install Docker MCP for Claude Desktop automatically via :

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

Prerequisites

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

Installation

Claude Desktop Configuration

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 💻 Development Configuration

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

🚀 Production Configuration

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

🛠️ Development

Local Setup

Clone the repository:

git clone 
cd docker-mcp

Create and activate a virtual environment:

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

Install dependencies:

uv sync

🔍 Debugging

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.

📝 Available Tools

The server provides the following tools:

create-container

Creates a standalone Docker container

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

deploy-compose

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'"

get-logs

Retrieves logs from a specific container

 "container_name": "my-container"

list-containers

Lists all Docker containers

🚧 Current Limitations

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

🤝 Contributing

Fork the repository from docker-mcp
Create your feature branch
Commit your changes
Push to the branch
Open a Pull Request

📜 License

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

✨ Authors

Alex Andru - Initial work | Core contributor - @QuantGeekDev
Ali Sadykov - Initial work | Core contributor - @md-archive Made with ❤️

How to Use

To use the docker-mcp, follow these steps:

Visit https://github.com/QuantGeekDev/docker-mcphttps://github.com/QuantG...
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using docker-mcp capabilities within your Claude conversations

Additional Information

Created

March 12, 2025

Company

QuantGeekDev

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More