An MCP server that lets AI assistants manage Docker containers, images, networks, volumes, Compose services, and registries through natural language. It supports Docker Hub and GHCR operations, system cleanup, exec commands, and safety confirmations for destructive actions.
From the registry: MCP server for managing Docker containers, images, networks, volumes, and registries

Please install the `docker-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 18+** — Node.js 18.0.0 or higher. (https://nodejs.org)
- **Docker daemon** — Docker daemon must be running and accessible.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["@alisaitteke/docker-mcp"]
- optional environment variables:
- `DOCKER_HOST`: Docker daemon host URL. (example: `tcp://localhost:2376`)
- `DOCKER_SOCKET_PATH`: Override platform default Docker socket path. (example: `/var/run/docker.sock`)
- `DOCKER_CERT_PATH`: Path to Docker certificates directory. (example: `/path/to/certs`)
- `DOCKER_TLS_VERIFY`: Enable TLS verification (1 or 0). (example: `1`)
- `DOCKER_PORT`: Docker daemon port. (example: `2376`)
- `DOCKER_PROTOCOL`: Protocol: http or https. (example: `https`)
Note: Auto-detects Docker socket location per platform. Supports local and remote Docker over TLS.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.DOCKER_HOSTDocker daemon host, including remote hosts or alternate local endpointsDOCKER_PORTDocker daemon portDOCKER_PROTOCOLProtocol to use for Docker connection (http or https)DOCKER_SOCKET_PATHPath to the Docker socket, overriding the platform defaultDOCKER_CERT_PATHPath to Docker certificates for TLS connectionsDOCKER_TLS_VERIFYEnable TLS verification when connecting to DockerReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.