ckreiling/mcp-server-docker

Overview

An MCP server that lets AI agents interact with Docker containers and images. It exposes Docker operations as tools via the Model Context Protocol, enabling agents to list containers, inspect images, and execute commands inside running containers.

Best for

Best for
Developers building AI agents that need to manage Docker containers programmatically

Use cases

• Automating container lifecycle management from an AI assistant
• Running diagnostic commands inside containers without manual SSH
• Integrating Docker operations into agentic workflows and pipelines

How to use

Tools exposed

• docker
• uvx

Tested with

Claude Desktop

Example client config

{\n  "mcp-server-docker": {\n    "command": "docker",\n    "args": [\n      "run",\n      "-i",\n      "--rm",\n      "-v",\n      "/var/run/docker.sock:/var/run/docker.sock",\n      "mcp-server-docker:latest"\n    ]\n  }\n}

Notes

An MCP server that lets AI agents interact with Docker containers and images. It exposes Docker operations as tools via the Model Context Protocol, enabling agents to list containers, inspect images, and execute commands inside running containers.

717 stars on GitHub. Last updated 2025-06-05. Licensed GPL-3.0.

Use cases

• Automating container lifecycle management from an AI assistant
• Running diagnostic commands inside containers without manual SSH
• Integrating Docker operations into agentic workflows and pipelines

Pros

• Simple Python implementation with clear MCP tool definitions
• Popular project with 717 stars indicating community trust
• Enables direct container interaction without custom scripting

Cons

• Limited to Docker operations exposed by the MCP server’s tool set
• Requires the MCP host to have Docker socket access, a security consideration
• No built-in support for Docker Compose or multi-container orchestration

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.