Docker Mcp Server

What is Docker Mcp Server?

Docker Mcp Server enables natural‑language interaction with Docker. It exposes a set of tools and resources that let an LLM compose, inspect, and control containers, images, networks, and volumes without writing Docker CLI commands.

How to use Docker Mcp Server?

1. Install – either install the Python package from PyPI using uvx mcp-server-docker or run the supplied Docker image after building it (docker build -t mcp-server-docker .).
2. Configure – add an entry to your MCP servers configuration, pointing to the command (uvx or docker run …) and, if needed, set DOCKER_HOST (e.g., ssh://user@host) for remote daemon access.
3. Interact – select one of the provided prompts (e.g., docker_compose) and describe the desired state in plain English. The server will generate a plan, apply it, and return status, logs, and stats.

Key Features

• Natural‑language composition – specify container setups, ports, and dependencies in everyday language.
• Live introspection – fetch container stats, logs, and status.
• Full Docker lifecycle tools – list/create/start/stop/remove containers, images, networks, and volumes.
• Remote Docker support – connect to a Docker daemon over SSH by setting DOCKER_HOST.
• Safety checks – disallows privileged mode and other high‑risk options.

Use Cases

• Server administrators managing production services (e.g., deploying a WordPress site) via chat.
• Developers experimenting locally with quick container prototypes.
• AI researchers testing LLM‑driven infrastructure automation.
• Education environments where learners can explore Docker without memorizing CLI syntax.

FAQ

Q: Can I store secrets in containers created by the server? A: No. The server deliberately blocks configuration that includes sensitive data. Use external secret management instead.

Q: Does the server support privileged containers? A: Not currently; privileged mode and custom capability flags are blocked for safety.

Q: How do I connect to a remote Docker host? A: Set DOCKER_HOST to an ssh:// URI in the MCP server definition.

Q: What programming language is the server written in? A: Python, using the Docker SDK (docker.from_env).

Q: Can I run the server itself in Docker? A: Yes. Build the image with docker build -t mcp-server-docker . and run it as shown in the README, mounting the Docker socket.

🐋 Docker MCP server

An MCP server for managing Docker with natural language!

🪩 What can it do?

• 🚀 Compose containers with natural language
• 🔍 Introspect & debug running containers
• 📀 Manage persistent data with Docker volumes

❓ Who is this for?

• Server administrators: connect to remote Docker engines for e.g. managing a public-facing website.
• Tinkerers: run containers locally and experiment with open-source apps supporting Docker.
• AI enthusiasts: push the limits of that an LLM is capable of!

Demo

A quick demo showing a WordPress deployment using natural language:

https://github.com/user-attachments/assets/65e35e67-bce0-4449-af7e-9f4dd773b4b3

🏎️ Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

If you don't have uv installed, follow the installation instructions for your system: link

Then add the following to your MCP servers file:

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

Purely for convenience, the server can run in a Docker container.

After cloning this repository, build the Docker image:

docker build -t mcp-server-docker .

And then add the following to your MCP servers file:

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

Note that we mount the Docker socket as a volume; this ensures the MCP server can connect to and control the local Docker daemon.

📝 Prompts

🎻 docker_compose

Use natural language to compose containers. See above for a demo.

Provide a Project Name, and a description of desired containers, and let the LLM do the rest.

This prompt instructs the LLM to enter a plan+apply loop. Your interaction with the LLM will involve the following steps:

1. You give the LLM instructions for which containers to bring up
2. The LLM calculates a concise natural language plan and presents it to you
3. You either:
   • Apply the plan
   • Provide the LLM feedback, and the LLM recalculates the plan

Examples

• name: nginx, containers: "deploy an nginx container exposing it on port 9000"
• name: wordpress, containers: "deploy a WordPress container and a supporting MySQL container, exposing Wordpress on port 9000"

Resuming a Project

When starting a new chat with this prompt, the LLM will receive the status of any containers, volumes, and networks created with the given project name.

This is mainly useful for cleaning up, in-case you lose a chat that was responsible for many containers.

📔 Resources

The server implements a couple resources for every container:

• Stats: CPU, memory, etc. for a container
• Logs: tail some logs from a container

🔨 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
• remove_network

Volumes

• list_volumes
• create_volume
• remove_volume

🚧 Disclaimers

Sensitive Data

DO NOT CONFIGURE CONTAINERS WITH SENSITIVE DATA. This includes API keys, database passwords, etc.

Any sensitive data exchanged with the LLM is inherently compromised, unless the LLM is running on your local machine.

If you are interested in securely passing secrets to containers, file an issue on this repository with your use-case.

Reviewing Created Containers

Be careful to review the containers that the LLM creates. Docker is not a secure sandbox, and therefore the MCP server can potentially impact the host machine through Docker.

For safety reasons, this MCP server doesn't support sensitive Docker options like --privileged or --cap-add/--cap-drop. If these features are of interest to you, file an issue on this repository with your use-case.

🛠️ Configuration

This server uses the Python Docker SDK's from_env method. For configuration details, see the documentation.

Connect to Docker over SSH

This MCP server can connect to a remote Docker daemon over SSH.

Simply set a ssh:// host URL in the MCP server definition:

"mcpServers": {
  "mcp-server-docker": {
    "command": "uvx",
    "args": [
      "mcp-server-docker"
    ],
    "env": {
      "DOCKER_HOST": "ssh://myusername@myhost.example.com"
    }
  }
}

💻 Development

Prefer using Devbox to configure your development environment.

See the devbox.json for helpful development commands.

After setting up devbox you can configure your Claude MCP config to use it:

  "docker": {
    "command": "/path/to/repo/.devbox/nix/profile/default/bin/uv",
    "args": [
      "--directory",
      "/path/to/repo/",
      "run",
      "mcp-server-docker"
    ]
  },