Docker Mcp

io.github.alisaitteke由 GitHub 账号 alisaitteke 发布v0.2.4更新于 Oct 24, 2026

MCP server for managing Docker containers, images, networks, volumes, and registries

发布方自己的服务:Docker Recipes

概览

AI 生成的概览

本地 MCP 服务器,让 AI 助手用自然语言管理 Docker 容器、镜像、网络、卷、Compose 项目与镜像仓库。

可以做什么
  • 列出、创建、启动、停止、重启、终止、暂停、检查与删除容器,并查看日志和统计
  • 拉取、推送、打标签、构建、检查与删除镜像,包括历史与分层信息
  • 创建、检查与删除网络和卷,并连接或断开容器
  • 在运行中的容器内执行命令并查看 exec 实例
  • 启动、停止、重启、构建与校验 Docker Compose 服务,查看其日志与状态
  • 查询系统信息与版本、监听事件、清理未使用资源,并搜索或登录 Docker Hub 与 GHCR
适用场景
适合希望让助手直接查看和操作本地或远程 Docker 环境的场景,例如确认哪些容器在运行、读取日志、在容器内执行命令,或启停 Compose 服务而无需切换到终端。
运行要求
通过 npx 或全局 npm 安装以 stdio 在本地运行;需要 Node.js 18 或更高版本,以及可访问的运行中 Docker 守护进程。套接字路径按平台自动检测;连接远程主机需设置 DOCKER_HOST、DOCKER_PORT、DOCKER_PROTOCOL、DOCKER_SOCKET_PATH、DOCKER_CERT_PATH 和 DOCKER_TLS_VERIFY,并可能需要网络访问与 TLS 证书。
安装前请注意
该服务器可以更改和销毁 Docker 状态:容器、镜像、网络和卷可被删除、终止或清理,也可在容器内执行命令。破坏性工具采用两步确认(confirm 参数或 MCP 交互确认),但该保护取决于客户端以及助手是否传入确认。镜像仓库工具会登录 Docker Hub 和 GHCR,仓库凭据会经过该服务器。将 DOCKER_HOST 指向远程守护进程即等于把同等控制权交给它。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Docker Mcp,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Docker MCP Server

Powerful Docker management for AI assistants

[npm version] [License: MIT] [Node.js Version]

A comprehensive Model Context Protocol (MCP) server that empowers AI assistants like Cursor, Claude Desktop, and other MCP-compatible clients to seamlessly manage Docker containers, images, networks, volumes, and registries through natural language interactions.

Why Docker MCP Server?

  • Zero Configuration - Works out of the box with npx, no installation needed
  • Safety First - Two-step confirmation for destructive operations
  • Cross-Platform - Works on Windows, Linux, and macOS with automatic Docker socket detection
  • Comprehensive - Full Docker API coverage including Compose, registries, and system operations
  • AI-Native - Designed specifically for AI assistants with clear, structured responses

[Features] Features

Container Management

  • Full lifecycle control: Create, start, stop, restart, kill, and remove containers
  • Monitoring: Real-time logs, statistics, and container inspection
  • Advanced operations: Pause/unpause, exec commands, and resource management

Image Management

  • Registry operations: Pull, push, tag, and remove images
  • Build support: Build images from Dockerfiles with full configuration
  • Inspection: Detailed image history, layers, and metadata

Network Management

  • Network operations: Create, remove, and inspect Docker networks
  • Container connectivity: Connect/disconnect containers from networks
  • Network discovery: List and filter networks with advanced options

Volume Management

  • Volume operations: Create, remove, and inspect volumes
  • Data persistence: Manage persistent storage for containers
  • Volume inspection: Detailed volume information and mount points

System Operations

  • System information: Docker daemon info, version, and capabilities
  • Resource cleanup: Prune unused images, containers, volumes, and networks
  • Event monitoring: Real-time Docker event stream

Container Execution

  • Command execution: Run commands in running containers
  • Interactive sessions: Create and manage exec instances
  • Output streaming: Real-time command output and logs

Registry Integration

  • Docker Hub: Search repositories, list tags, authenticate, pull/push images
  • GitHub Container Registry (GHCR): Full authentication and image management
  • Multi-registry support: Seamlessly work with multiple registries

Docker Compose Support

  • Multi-container management: Start, stop, restart compose services
  • Service monitoring: View logs and status of compose services
  • Build operations: Build compose services with dependency management
  • Configuration validation: Parse and validate docker-compose.yml files

Safety Features

  • Two-step confirmation for all destructive operations
  • Resource preview: See what will be deleted before confirmation
  • Dual confirmation methods:
    • Confirm parameter (default): Works everywhere, simple and reliable
    • MCP Elicitation API (advanced): Interactive form-based confirmation for better UX

[Installation] Installation

Via npx (Recommended)

bash
npx @alisaitteke/docker-mcp

Local Installation

bash
npm install -g @alisaitteke/docker-mcp

Or install locally in your project:

bash
npm install @alisaitteke/docker-mcp

[Quick Start] Quick Start

With Cursor

  1. Add to your Cursor MCP configuration (usually in .cursor/mcp.json or similar):
json
{  "mcpServers": {    "docker": {      "command": "npx",      "args": ["@alisaitteke/docker-mcp"]    }  }}
  1. Restart Cursor and start managing Docker with AI!

With Claude Desktop

  1. Add to your Claude Desktop configuration:
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • Linux: ~/.config/Claude/claude_desktop_config.json
json
{  "mcpServers": {    "docker": {      "command": "npx",      "args": ["@alisaitteke/docker-mcp"]    }  }}
  1. Restart Claude Desktop and start managing Docker with AI!

Local Development and Testing

Prerequisites

  • Node.js 18.0.0 or higher
  • Docker daemon running
  • npm or yarn

Setup

  1. Clone the repository:
bash
git clone <repository-url>cd docker-mcp
  1. Install dependencies:
bash
npm install
  1. Build the project:
bash
npm run build

Running Locally

Method 1: Using npm start (after build)
bash
# Build firstnpm run build
# Run the servernpm start
Method 2: Using npm run dev (development mode with tsx)
bash
npm run dev

This uses tsx to run TypeScript directly without building.

Method 3: Direct execution
bash
# Build firstnpm run build
# Run directly with nodenode dist/index.js
Method 4: Using the binary
bash
# Build firstnpm run build
# Make sure the binary is executablechmod +x bin/docker-mcp-server.js
# Run the binary./bin/docker-mcp-server.js

Development Workflow

  1. Make changes to source files in src/
  2. Build the project:
bash
npm run build
  1. Test the changes:
bash
npm start# ornpm run dev
  1. Check for TypeScript errors:
bash
npm run typecheck
  1. Lint the code:
bash
npm run lint

Troubleshooting

Docker connection issues:

  • Ensure Docker daemon is running: docker ps
  • Linux/macOS: Check Docker socket permissions: ls -la /var/run/docker.sock
  • Windows: Ensure Docker Desktop is running and named pipe is accessible
  • For remote Docker, set environment variables: DOCKER_HOST, DOCKER_CERT_PATH, etc.
  • macOS: If /var/run/docker.sock doesn't exist, try ~/.docker/run/docker.sock (Docker Desktop 4.0+)

Build errors:

  • Clear node_modules and reinstall: rm -rf node_modules && npm install
  • Check TypeScript version compatibility
  • Ensure all dependencies are installed: npm install

Runtime errors:

  • Check that Docker is accessible: docker version
  • Verify the build was successful: ls -la dist/
  • Check server logs (errors are written to stderr)

[Configuration] Configuration

The server automatically detects the operating system and uses the appropriate Docker socket path:

Platform-Specific Defaults

  • Linux: /var/run/docker.sock (Unix socket)
  • macOS: /var/run/docker.sock or ~/.docker/run/docker.sock (Docker Desktop 4.0+)
  • Windows: //./pipe/docker_engine (Named pipe)

Connection Methods (in order of priority)

  1. Environment variables (highest priority):

    • DOCKER_HOST - Docker daemon host (e.g., tcp://localhost:2376, npipe:////./pipe/docker_engine)
    • DOCKER_PORT - Docker daemon port
    • DOCKER_PROTOCOL - Protocol (http or https)
    • DOCKER_SOCKET_PATH - Path to Docker socket (overrides platform default)
    • DOCKER_CERT_PATH - Path to Docker certificates directory
    • DOCKER_TLS_VERIFY - Enable TLS verification (1 or 0)
  2. Platform-specific defaults (automatic detection):

    • Linux: /var/run/docker.sock
    • macOS: /var/run/docker.sock (or ~/.docker/run/docker.sock if available)
    • Windows: //./pipe/docker_engine

Windows Configuration

On Windows, Docker Desktop uses named pipes. The server automatically detects Windows and uses the correct path. You can also explicitly set:

bash
# Using environment variableset DOCKER_SOCKET_PATH=//./pipe/docker_engine
# Or using DOCKER_HOSTset DOCKER_HOST=npipe:////./pipe/docker_engine

Remote Docker Host

To connect to a remote Docker host:

bash
# Linux/macOSexport DOCKER_HOST=tcp://192.168.1.100:2376export DOCKER_TLS_VERIFY=1export DOCKER_CERT_PATH=/path/to/certs
# Windowsset DOCKER_HOST=tcp://192.168.1.100:2376set DOCKER_TLS_VERIFY=1set DOCKER_CERT_PATH=C:\path\to\certs

[Available Tools] Available Tools

Container Tools

  • docker_list_containers - List all containers
  • docker_create_container - Create a new container
  • docker_start_container - Start a container
  • docker_stop_container - Stop a container
  • docker_restart_container - Restart a container
  • docker_kill_container - Kill a container
  • docker_remove_container - Remove a container
  • docker_inspect_container - Get container details
  • docker_container_logs - Get container logs
  • docker_container_stats - Get container statistics
  • docker_pause_container - Pause a container
  • docker_unpause_container - Unpause a container

Image Tools

  • docker_list_images - List all images
  • docker_pull_image - Pull an image from registry
  • docker_push_image - Push an image to registry
  • docker_tag_image - Tag an image
  • docker_remove_image - Remove an image
  • docker_inspect_image - Get image details
  • docker_image_history - Get image history

Network Tools

  • docker_list_networks - List all networks
  • docker_create_network - Create a network
  • docker_remove_network - Remove a network
  • docker_inspect_network - Get network details
  • docker_connect_container - Connect container to network
  • docker_disconnect_container - Disconnect container from network

Volume Tools

  • docker_list_volumes - List all volumes
  • docker_create_volume - Create a volume
  • docker_remove_volume - Remove a volume
  • docker_inspect_volume - Get volume details

System Tools

  • docker_system_info - Get Docker system information
  • docker_version - Get Docker version
  • docker_prune_system - Prune all unused resources
  • docker_prune_images - Prune unused images
  • docker_prune_containers - Prune stopped containers
  • docker_prune_volumes - Prune unused volumes
  • docker_prune_networks - Prune unused networks

Exec Tools

  • docker_exec - Execute a command in a container
  • docker_inspect_exec - Get exec instance details

Compose Tools

  • docker_compose_up - Start Docker Compose services
  • docker_compose_down - Stop and remove Docker Compose services
  • docker_compose_ps - List Docker Compose services
  • docker_compose_logs - View output from Docker Compose services
  • docker_compose_config - Parse and validate docker-compose.yml file
  • docker_compose_build - Build Docker Compose services
  • docker_compose_restart - Restart Docker Compose services
  • docker_compose_stop - Stop Docker Compose services
  • docker_compose_start - Start Docker Compose services

Registry Tools

  • dockerhub_search - Search Docker Hub
  • dockerhub_get_tags - Get repository tags from Docker Hub
  • dockerhub_authenticate - Authenticate with Docker Hub
  • dockerhub_pull - Pull from Docker Hub
  • dockerhub_push - Push to Docker Hub
  • ghcr_authenticate - Authenticate with GitHub Container Registry
  • ghcr_pull - Pull from GHCR
  • ghcr_push - Push to GHCR

[Examples] Examples

List running containers

json
{  "name": "docker_list_containers",  "arguments": {    "all": false  }}

Create and start a container

json
{  "name": "docker_create_container",  "arguments": {    "image": "nginx:latest",    "name": "my-nginx",    "ports": {"80/tcp": {}}  }}

Then start it:

json
{  "name": "docker_start_container",  "arguments": {    "id": "my-nginx"  }}

Pull an image from Docker Hub

json
{  "name": "docker_pull_image",  "arguments": {    "name": "ubuntu:20.04"  }}

Search Docker Hub

json
{  "name": "dockerhub_search",  "arguments": {    "query": "node",    "limit": 10  }}

Execute a command in a container

json
{  "name": "docker_exec",  "arguments": {    "containerId": "my-container",    "cmd": ["ls", "-la"],    "tty": false  }}

Start Docker Compose services

json
{  "name": "docker_compose_up",  "arguments": {    "projectDir": "/path/to/compose/project",    "detach": true,    "build": true  }}

View Compose logs

json
{  "name": "docker_compose_logs",  "arguments": {    "projectDir": "/path/to/compose/project",    "follow": false,    "tail": 100  }}

Removing Resources with Confirmation

All destructive operations (remove, kill, prune) support two confirmation methods:

Method 1: Confirm Parameter (Default - Works Everywhere)

Step 1: Preview (without confirm)

json
{  "name": "docker_remove_volume",  "arguments": {    "name": "my-volume"  }}

This returns volume details and a warning message.

Step 2: Confirm (with confirm=true)

json
{  "name": "docker_remove_volume",  "arguments": {    "name": "my-volume",    "confirm": true  }}

This actually removes the volume.

Method 2: MCP Elicitation API (Advanced - Better UX)

If your MCP client (Cursor, Claude Desktop) supports Elicitation API, you can use interactive confirmation:

json
{  "name": "docker_remove_volume",  "arguments": {    "name": "my-volume",    "useElicitation": true  }}

This will show an interactive confirmation dialog in the client (if supported). The client will display a form asking for confirmation, and the operation proceeds only if the user accepts.

Note: Elicitation API support depends on the MCP client. If the client doesn't support it, the server automatically falls back to the confirm parameter method.

Operations requiring confirmation:

  • docker_remove_volume - Remove volumes
  • docker_remove_container - Remove containers
  • docker_kill_container - Kill containers
  • docker_remove_image - Remove images
  • docker_remove_network - Remove networks
  • docker_prune_system - Prune all unused resources
  • docker_prune_images - Prune unused images
  • docker_prune_containers - Prune stopped containers
  • docker_prune_volumes - Prune unused volumes
  • docker_prune_networks - Prune unused networks

Testing the Server

Quick Test

  1. Build the project:
bash
npm run build
  1. Use the test script:
bash
./test-server.sh

Or test manually:

  1. Test Docker connection:
bash
# The server will exit with error if Docker is not accessiblenode dist/index.js

If Docker is running, you should see:

Docker MCP Server running on stdio
  1. Test with a simple MCP request (using jq for JSON formatting):
bash
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node dist/index.js | jq

Note: The server communicates via stdio, so it will wait for JSON-RPC requests. Press Ctrl+C to exit.

Manual Testing Steps

  1. Start the server:
bash
npm run buildnpm start
  1. In another terminal, test with curl (if using HTTP transport) or use an MCP client

  2. Verify Docker operations work:

    • List containers: Use docker_list_containers tool
    • Check system info: Use docker_system_info tool

Integration Testing

For full integration testing, you'll need an MCP client. The server communicates via stdio (standard input/output), so it's designed to work with MCP-compatible clients like:

  • Cursor IDE
  • Claude Desktop
  • Custom MCP clients

Debugging

Enable verbose logging by checking stderr output. The server writes errors and status messages to stderr:

bash
# Run and capture stderrnode dist/index.js 2> debug.log

[Requirements] Requirements

  • Node.js 18.0.0 or higher
  • Docker daemon running and accessible
  • Supported Platforms:
    • Linux (x64, ARM64)
    • macOS (Intel, Apple Silicon)
    • Windows (x64, ARM64)
  • For remote Docker: Proper network access and TLS certificates (if using TLS)

Platform-Specific Notes

  • Linux: Requires Docker daemon with Unix socket at /var/run/docker.sock
  • macOS: Works with Docker Desktop. Automatically detects socket location.
  • Windows: Works with Docker Desktop. Uses named pipe //./pipe/docker_engine

Quick Start (Local Development)

bash
# Clone and setupgit clone <repository-url>cd docker-mcpnpm install
# Buildnpm run build
# Test./test-server.sh
# Runnpm start# or for developmentnpm run dev

License

MIT

Testing with MCP Clients

Testing with Cursor (Local Development)

If you're developing locally and want to test with Cursor:

  1. Build the project:
bash
npm run build
  1. Add to Cursor MCP configuration (usually in .cursor/mcp.json or similar):
json
{  "mcpServers": {    "docker": {      "command": "node",      "args": ["/absolute/path/to/docker-mcp/dist/index.js"]    }  }}

Or if using the binary:

json
{  "mcpServers": {    "docker": {      "command": "/absolute/path/to/docker-mcp/bin/docker-mcp-server.js"    }  }}

Testing with Claude Desktop (Local Development)

If you're developing locally and want to test with Claude Desktop:

  1. Build the project:
bash
npm run build
  1. Add to Claude Desktop configuration:
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • Linux: ~/.config/Claude/claude_desktop_config.json
json
{  "mcpServers": {    "docker": {      "command": "node",      "args": ["/absolute/path/to/docker-mcp/dist/index.js"]    }  }}

Testing with MCP Inspector (CLI)

You can test the server using MCP Inspector or any MCP client:

bash
# Build firstnpm run build
# The server communicates via stdio, so you can pipe commands to itecho '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node dist/index.js

[Contributing] Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

来源:README.md,提交 b4f9de5

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.2.4最新Sep 16, 2026

评分

已满足适用检查项的 40%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Docker 集成