Docker MCP Server

More than just a fully featured MCP server that lets AI agents manage the full surface of Docker — containers, images, networks, volumes, swarm

Local serverstdioPython

What is the Docker MCP server?

More than just a fully featured MCP server that lets AI agents manage the full surface of Docker — containers, images, networks, volumes, swarm services, secrets, configs, nodes, plugins, etc., it helps you create workfl. Exposed over MCP by the docker mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Adding it to your client

install. on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

  • Linux — ** -v /var/run/docker.sock:/var/run/docker.sock (rootless: -v $XDG_RUNTIME_DIR/docker.sock:/var/run/docker.sock)
  • Variant — Tags
  • no-scout — :no-scout, :-no-scout

Configuration

You will need 4 environment variables: DOCKER_HOST, DOCKER_TLS_VERIFY, DOCKER_CERT_PATH, DOCKER_MCP_SERVER_HOSTS. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Note: If you're using the containerized MCP server or MCPB bundle, the Python and uv requirements are taken care of for you. - A running Docker daemon reachable from the host that runs the server (the standard DOCKER_HOST / unix socket conventions apply) - Python ≥ 3.14 - uv for dependency management

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the docker mcp server does with a few real requests.

When to reach for it

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Docker's toolset — Linux, Variant, no-scout — is a fair guide to whether it matches your workflow. It is maintained by L337.org; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
Linux** -v /var/run/docker.sock:/var/run/docker.sock (rootless: -v $XDG_RUNTIME_DIR/docker.sock:/var/run/docker.sock).
VariantTags
no-scout:no-scout, :<version>-no-scout

How to install the Docker MCP server

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

Configuration as documented by the project. Restart the client after saving.

Configuration

Note: If you're using the containerized MCP server or MCPB bundle, the Python and uv requirements are taken care of for you. - A running Docker daemon reachable from the host that runs the server (the standard DOCKER_HOST / unix socket conventions apply) - Python ≥ 3.14 - uv for dependency management

VariableDescriptionRequired
DOCKER_HOSTEndpoint or connection string the server talks to.Optional
DOCKER_TLS_VERIFYConfiguration value read at startup.Optional
DOCKER_CERT_PATHFilesystem location the server is allowed to use.Optional
DOCKER_MCP_SERVER_HOSTSEndpoint or connection string the server talks to.Optional

Example prompts to try

  • Use Docker to Linux.
  • Use Docker to Variant.
  • Use Docker to no-scout.

Frequently asked questions

The source code is linked from the repository URL on this page.