MCP ServerSTDIO

Docker MCP Server

The Docker MCP server gives AI models structured access to your local Docker environment — list running containers, inspect images, read logs, execute commands inside containers and manage Docker Compose services. Runs via Docker Desktop or the Docker CLI with no extra infrastructure.

Hosted URL

Bring your own

Suggested model

Claude Sonnet 4.5

MCP Playground runs 30+ models on the same workflow: switch anytime, or use Compare mode to run several in parallel and balance quality vs. cost.

Auth

No token required

What the Docker MCP server does

How models use it and what it is built for.

Docker's MCP integration exposes the Docker Engine API as MCP tools. Models can list all containers (running or stopped), inspect container configuration and resource usage, read stdout/stderr logs, run one-off commands inside a container, pull images, inspect image layers and manage Docker Compose stacks. It connects through the Docker socket on your machine, so Docker Desktop (or Docker Engine on Linux) must be running. The server is part of Docker's official MCP Catalog and is open source. It requires no API key — just a running Docker installation.

Tools the Docker MCP server exposes

Typical tools an AI model can call. Exact names vary by version.

  • list_containers — list running and stopped containers with status
  • inspect_container — get detailed config, mounts, ports and resource limits
  • get_logs — stream stdout/stderr logs from a container
  • exec_command — run a command inside a running container
  • list_images / pull_image — manage local Docker images
  • docker_compose — start, stop and inspect Docker Compose services

Example prompts to try

Copy any of these into MCP Agent Studio after connecting.

  • List all running containers and how long they have been up.

  • Show me the last 50 lines of logs from the "api" container.

  • Which containers are using more than 500MB of memory right now?

  • Run "npm test" inside the "app" container and show me the output.

Models on MCP Playground

This is not a single-model product: you get the same MCP connection with 30+ models (Claude, GPT, Gemini, DeepSeek, open-weight, and more), you can switch mid-conversation, and you can open Compare mode to run the same prompt against multiple models at once. The card above is a suggested starting point for this server — not the only choice.

Default pick for Docker

Claude Sonnet 4.5

Claude Sonnet 4.5 handles multi-step DevOps reasoning and log analysis well. Use Haiku for simple container listing; Opus for complex Compose debugging.

Try the Docker MCP server in your browser

Open MCP Agent Studio with the connection pre-filled. Add your token, pick any of 30+ models, and start chatting — no install required.

Open Agent Studio

Docker MCP server — FAQ

Common questions about connecting, scoping and using it safely.

What is the Docker MCP server?

It is an official open-source MCP server from Docker that lets AI models interact with your local Docker environment. Agents can list containers, read logs, run commands inside containers and manage images — all from a natural language chat.

Do I need Docker Desktop or just Docker CLI?

Either works. The server connects to the Docker socket, which Docker Desktop, Docker Engine (Linux) and Docker CLI all expose. On macOS, Docker Desktop is the easiest path.

Is the Docker MCP server free?

Yes. The server itself is free and open source. Docker Desktop is free for personal use and small businesses. AI model usage is billed by your model provider.

Can the AI agent start or stop my containers?

Yes — start, stop, restart and remove tools are available. Always confirm before the agent takes a destructive action. For read-only monitoring workflows, you can restrict access at the Docker socket level.

How is Docker MCP different from running docker CLI commands?

The CLI requires you to know the exact commands. Docker MCP lets you describe what you want in plain English and the AI agent figures out the right Docker API calls, chains multiple operations, and explains the results in a readable format.

Other MCP servers

More on MCP Playground