nideil

Docker MCP Server

Community nideil
Updated

Docker's MCP Server

Docker MCP Server

The Docker MCP Server is a Model Context Protocol (MCP)server that provides seamless integration with Docker Desktop on Windows, enabling advancedautomation and interaction capabilities for developers and tools.

Prerequisites

  1. Install Docker Desktop for Windows from Docker's official download page.

  2. In Docker Desktop, go to Settings > General and check the box for "Expose daemon on tcp://localhost:2375 without TLS". This is required for the MCP server to communicate with Docker Desktop.

    ๐Ÿ’ก Tip: You can verify that the port is exposed successfully by opening http://localhost:2375/version in your browser. If the setup is correct, you should see a JSON response with Docker version information.If you're having trouble, check this discussion for a possible solution:WSL and Docker for Windows: Cannot connect to the Docker daemon

Installation

Usage with Claude Desktop

{
  "mcpServers": {
    "docker-mcp-stdio": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "freezeolo/docker-mcp-server"
      ]
    }
  }
}

Tools

โœ… Completed ๐Ÿ› ๏ธ In Progress โŒ Plan

Container Lifecycle Management โœ…

  • list_containers - Get the list of containers โœ…
  • get_container_info - Get details of a specific container โœ…
    • container_id: Container ID (string, required)
  • start_container - Start a container โœ…
    • container_id: Container ID (string, required)
  • restart_container - Restart a container โœ…
    • container_id: Container ID (string, required)
  • stop_container - Stop a container โœ…
    • container_id: Container ID (string, required)
  • remove_container - Remove a container โœ…
    • container_id: Container ID (string, required)
  • create_container - Create a new container โœ…
    • imageName: Image name (string, required)
    • containerName: Container name (string, required)
    • command: Command to run (string, optional)
    • env: Environment variables (string[], optional)
    • ports: Port bindings (string[], optional)
    • volumes: Volume bindings (string[], optional)
    • network: Network name (string, optional)
    • restartPolicy: Restart policy (string, optional)

Network Management โœ…

  • list_networks - List all networks โœ…
  • get_network_info - Get network information โœ…
    • networkId: Network ID (string, required)
  • create_network - Create a new network โœ…
    • networkName: Network name (string, required)
    • driver: Network driver (string, required)
    • subnet: Subnet CIDR (string, required)
    • gateway: Gateway IP (string, required)
  • connect_container_to_network - Connect container to network โœ…
    • containerId: Container ID (string, required)
    • networkId: Network ID (string, required)
  • disconnect_container_from_network - Disconnect container from network โœ…
    • containerId: Container ID (string, required)
    • networkId: Network ID (string, required)
  • remove_network - Remove a network โœ…
    • networkId: Network ID (string, required)
  • get_network_containers - Get containers in a network โœ…
    • networkId: Network ID (string, required)

Image Management โœ…

  • list_images - List all images โœ…
  • pull_image - Pull an image from registry โœ…
    • imageName: Image name with tag (string, required)
  • push_image - Push an image to registry โœ…
    • imageName: Image name with tag (string, required)
  • remove_image - Remove an image โœ…
    • imageId: Image ID (string, required)
    • force: Force removal (boolean, optional)
  • tag_image - Tag an image with multiple tags โœ…
    • imageId: Image ID (string, required)
    • repository: Repository name (string, required)
    • tags: Array of tags (string[], required)
  • build_image - Build an image from Dockerfile โœ…
    • dockerfilePath: Path to Dockerfile (string, required)
    • repository: Repository name (string, required)
    • tags: Array of tags (string[], required)
  • get_image_details - Get image details โœ…
    • imageId: Image ID (string, required)

Logs Management โœ…

  • get_container_logs - Get container logs โœ…
    • containerId: Container ID (string, required)
    • follow: Follow log output (boolean, optional, default: false)
    • stdout: Show stdout (boolean, optional, default: true)
    • stderr: Show stderr (boolean, optional, default: true)
    • since: Show logs since timestamp (string, optional)
    • until: Show logs until timestamp (string, optional)
    • tail: Number of lines to show from the end (integer, optional)
    • timestamps: Show timestamps (boolean, optional, default: false)

FAQ

Q: How do I install the project?

A: Follow the steps in the Installation section. Make sure you have the required dependencies.

License

This project is licensed under the terms of the MIT open source license. Please refer to MIT for the full terms.

MCP Server ยท Populars

MCP Server ยท New

    aovestdipaperino

    tokensave

    Rust port of CodeGraph โ€” a local-first code intelligence system that builds semantic knowledge graphs from codebases. Ported from the original TypeScript implementation by @colbymchenry.

    Community aovestdipaperino
    jpicklyk

    MCP Task Orchestrator

    Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency graphs, quality gates, and actor attribution. Schemas define what agents must produce โ€” the server blocks the call if they don't. Works with any MCP-compatible client.

    Community jpicklyk
    AgentsID-dev

    AgentsID Scanner

    Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.

    Community AgentsID-dev
    remete618

    widemem.ai

    Next-gen AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization

    Community remete618
    Ruya-AI

    Cozempic

    Context cleaning for Claude Code โ€” prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning

    Community Ruya-AI