Docker Management MCP Server

Developer ToolsPython

Manage Docker containers and compose stacks through Claude AI

Available Tools

create-container

Creates a standalone Docker container with specified image, name, ports, and environment variables

imagenameportsenvironment

deploy-compose

Deploys a Docker Compose stack using the provided YAML configuration

project_namecompose_yaml

get-logs

Retrieves logs from a specific Docker container

container_name

list-containers

Lists all Docker containers on the system

Docker Management is a powerful Model Context Protocol server that enables seamless Docker operations through Claude AI. It allows you to create and manage containers, deploy Docker Compose stacks, retrieve container logs, and monitor container status directly from your AI assistant. With this tool, developers can streamline their Docker workflow by leveraging natural language commands to perform common Docker operations without switching contexts or remembering complex command syntax. The server bridges the gap between AI assistants and container management, making DevOps tasks more accessible and efficient.

Overview

Docker Management is a Model Context Protocol (MCP) server that enables Claude to interact with Docker on your system. This integration allows you to manage containers, deploy compose stacks, view logs, and monitor container status through natural language interactions with Claude.

Prerequisites

Before installing Docker Management, ensure you have:

Python 3.12 or higher
UV package manager
Docker Desktop or Docker Engine
Claude Desktop application

Installation

Option 1: Install via Smithery (Recommended)

The easiest way to install Docker Management is through Smithery:

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

This automatically configures Claude Desktop to use the Docker Management MCP.

Option 2: Manual Installation

Install the package using UV:

uvx install docker-mcp

Configure Claude Desktop by editing the configuration file:

For macOS: Edit ~/Library/Application\ Support/Claude/claude_desktop_config.json

For Windows: Edit %APPDATA%/Claude/claude_desktop_config.json

Add the following configuration:

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

Restart Claude Desktop to apply the changes.

Usage

Once installed, you can interact with Docker through Claude using natural language. Here are some example prompts:

"Create a new Nginx container exposed on port 8080"
"Deploy a WordPress and MySQL stack using Docker Compose"
"Show me the logs for my container named 'web-server'"
"List all running Docker containers"

Working with Docker Compose

To deploy a multi-container application with Docker Compose, you can ask Claude to create and deploy a compose file. For example:

"Deploy a Docker Compose stack with Redis and a Python web application that connects to it."

Claude will use the deploy-compose tool to create the necessary configuration and deploy the stack.

Debugging

If you encounter issues, you can use the MCP Inspector for debugging:

npx @modelcontextprotocol/inspector uvx docker-mcp

This will provide a web interface where you can monitor the communication between Claude and the Docker Management MCP.

Limitations

The current version has some limitations:

Limited support for environment variables in containers
No volume management capabilities
No network management features
No container health checks
No container restart policy configuration
No container resource limits management

These features may be added in future versions of the tool.