🐋 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 apublic-facing website.
Tinkerers: spin up containers locally, without running a single commandyourself.

🏎️ Quickstart

Prerequisites

Ensure you have uv installed (seethe docs fordetails)
Clone this repository

Install

Claude Desktop

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

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

Development/Unpublished Servers Configuration

"mcpServers": {
  "mcp-server-docker": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/repo",
      "run",
      "mcp-server-docker"
    ]
  }
}

📝 Prompts

🎻 `docker_compose`

Use natural language to compose containers.

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

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

You give the LLM instructions for which containers to bring up
The LLM calculates a concise natural language plan and presents it to you
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 port9000"
name: wordpress, containers: "deploy a WordPress container and a supportingMySQL container, exposing Wordpress on port 9000"

Resuming a Project

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

This is mainly useful for cleaning up, in-case you lose a chat that wasresponsible 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 theLLM is running on your local machine.

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

Reviewing Created Containers

Be careful to review the containers that the LLM creates. Docker is not a securesandbox, and therefore the MCP server can potentially impact the host machinethrough Docker.

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

🛠️ Configuration

This server uses the Python Docker SDK's from_env method. For configurationdetails, seethe documentation.

💻 Development

Prefer using Devbox to configure your development environment.

See the devbox.json for helpful development commands.

🐋 Docker MCP server