Docker MCP in Claude Code

Quick answer: Install the Docker MCP server with npx -y mcp-server-docker, add the JSON block below to ~/.claude/settings.json, restart Claude Code, and run /mcp to confirm the connection. Setup runs about 5 minutes on a fresh machine, verified on mcp-server-docker as of April 15, 2026.

The Docker MCP server hands Claude Code a tool surface on your local Docker daemon. After setup, the model can list containers, start and stop them, read logs, exec into a running container, and manage images. The server is published as mcp-server-docker and uses the local Docker socket for access, no API key required.

This guide covers what you get after the wiring is done, the exact config, verification steps, prompt patterns that tend to work well, and the 4 issues that trip people up most often in the first week.

What you get when it is connected

Once the Docker server is attached, Claude Code can call the server tools from inside any conversation. You do not invoke the tools by hand. When you ask Claude a question the model decides which tool to call and parses the response for you. For teams that live inside Docker day to day, this replaces dozens of context switches per week with a single line in chat.

Tools exposed include list_containers, inspect_container, create_container, start_container, stop_container, remove_container, logs, exec, list_images, pull_image, prune. The exec tool is particularly handy for one-off debugging, but it does not preserve state across calls - each exec spawns a fresh process.

Prerequisites

A running Docker daemon (Docker Desktop on macOS or Windows, or dockerd on Linux). Your user must be in the docker group or have access to the socket. Node 20 or later.

If you use a version manager like nvm or asdf for Node, confirm the version Claude Code inherits. Open a terminal, run node -v, and note the output. Claude Code uses the Node it sees on PATH at launch, so a shell profile that sets the right version is the reliable path.

Install via npx

Run the package once with npx to verify it starts cleanly:

npx -y mcp-server-docker

The first run downloads the package (a few MB) and starts the server on stdio. The server does not print much on success - it waits for MCP protocol messages on stdin. Press Ctrl-C to stop it. The actual runtime setup happens through Claude Code itself in the next step.

If the install fails with a network error, your npm registry may be blocked. Set npm config set registry https://registry.npmjs.org and retry. Behind a corporate proxy, also set HTTP_PROXY and HTTPS_PROXY in your shell.

Add the config block to ~/.claude/settings.json

Open ~/.claude/settings.json in your editor. If the file does not exist yet, create it with {} as the starting content. Add an mcpServers object with an entry for this server:

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

Save the file. If you already have other MCP servers defined, merge the new entry into the existing mcpServers object rather than replacing it.

Restart Claude Code fully (quit and reopen, not just close the window). The server is spawned lazily on the first tool call in a session, not at launch, but the config is read once per Claude Code start.

Verify the connection

Open a new Claude Code session and type /mcp at the prompt. You should see the server listed with a green or connected indicator. If it shows as failed, click into it for the stderr output - the error message usually points at the problem directly (bad token, wrong path, missing Node).

Run a trivial first prompt to confirm round trips work. Good smoke tests:

• For read servers: ask for a list of whatever resource type it exposes.
• For write servers: ask for a describe on a known resource first, then try a safe write on a test resource.

If the first prompt works, the wiring is done. From here on you interact with the server purely through normal prompts in Claude Code.

Example prompts that work well

Here are prompts that tend to get good responses once the server is attached:

• List every running container and tell me how long each has been up and which image it uses.
• Show the last 500 log lines for container web-server-1 filtered for lines containing error.
• Pull the image postgres:16-alpine and tell me when it finishes.
• Stop all containers with the label project equal to staging.
• Exec the command ls /app in container api-worker-2 and show the output.
• Prune dangling images and tell me how much disk space was reclaimed.

Claude will chain tool calls on its own when the prompt implies several steps. For a summarize-then-write flow the model will often call read tools first, then a single write tool at the end. If a prompt keeps burning tool calls, narrow it: specify the resource ID, the time range, or the exact field you want rather than asking Claude to scan everything.

Environment variable security

No env vars required for the default local socket. For remote Docker engines, set DOCKER_HOST to the tcp:// URL and make sure TLS certs are in place at DOCKER_CERT_PATH. Claude inherits these from the shell it was launched from. Never expose the Docker socket over plain TCP without TLS - it is equivalent to root access on the host.

A general rule across every MCP server: never paste secrets directly into settings.json that lives in a shared or git-tracked directory. Keep the actual secret values in your shell profile (~/.zshrc, ~/.bashrc, or a 1Password-cli helper), export them at shell start, and reference the variable names from the Claude config. That way the secret stays on your machine and the config file is safe to share with teammates.

On macOS, terminals launched from Spotlight or from the Dock both inherit the shell profile. If you launch Claude Code from a GUI shortcut that does not go through a shell, env vars may not propagate - launch from a terminal instead.

Troubleshooting

Tool calls fail with permission denied on socket. Your user is not in the docker group. On Linux, run sudo usermod -aG docker $USER, log out and back in, then restart Claude Code. On macOS, make sure Docker Desktop is running.

Tool calls time out. The daemon is not responding. Try docker ps from a terminal. If that hangs too, restart Docker Desktop or the docker service. A daemon restart usually clears stuck operations.

Image pulls fail with not found. The image name or tag is wrong, or the registry needs auth. For private registries, log in with docker login first. The session auth is stored in ~/.docker/config.json and picked up by the server.

Logs tool returns nothing. The container is writing logs to a file rather than stdout/stderr. Check the docker-compose or Dockerfile; only output to stdout and stderr is visible through docker logs.

For any issue not listed here, the first step is /mcp inside Claude Code to see the current status and any recent stderr from the server. The second step is running the exact npx command from your terminal to see if the server starts cleanly outside Claude Code. Between those two checks, most problems become obvious within a minute.

Next steps

Once the Docker server is attached and verified, the useful next move is writing a short prompt template you keep in your notes. List the 3 or 4 prompts you run most often against this server, and paste them into Claude Code when needed. Over a few weeks you build a personal command library that gets real work done without typing much.

For team projects, commit a .mcp.json at the repo root with the same structure. Everyone on the team gets the server wired up automatically on first open, and individual secrets stay in shell profiles. That is the setup pattern that scales past a single developer.