Container Exec MCP Server
Enables AI assistants to manage Docker containers, execute commands inside them, and inspect container information through a minimalist set of tools supporting both stdio and HTTP transports.
README
Container Exec MCP Server

A Model Context Protocol (MCP) server that provides Docker container automation capabilities. This server enables AI assistants like Claude/Cursor/ChatGPT to manage and interact with Docker containers, execute commands, and inspect container information.
This package minimizes the amount of tools to help AI Agents pick the right tool for a given prompt.
Features
- 🐳 Container Management - List and inspect Docker containers
- 🔧 Command Execution - Execute commands inside containers
- 📊 Detailed Information - Get comprehensive container details
- 🚀 Dual Transport - HTTP and stdio (for Claude Code/Cursor)
For detailed information about available tools, see tools.md.
Table of Contents
- Container Exec MCP Server
Getting Started
Prerequisites
- Node.js 18 or higher
- Docker installed and running
- npm or yarn
Configuration
Environment Variables
Configure the server behavior using environment variables:
| Variable | Description | Default | Options |
|---|---|---|---|
PORT |
HTTP server port | 4200 |
Any valid port number |
MCP_AUTH_TOKEN |
Authentication token for HTTP server (optional) | None | Any string |
Cursor / Claude Code / Claude Desktop Configuration
To use this server with Cursor/Claude Code/Claude Desktop, add it to your MCP settings file.
Configuration:
{
"mcpServers": {
"container-exec": {
"command": "npx",
"args": [
"container-exec-mcp"
]
}
}
}
Note: After updating the configuration, restart Claude Code/Desktop for changes to take effect.
Important: Ensure Docker is running and accessible on your system.
HTTP Transport (for n8n or other HTTP clients)
Start the HTTP server:
npm install
npm start
# or with custom port
PORT=4200 npm start
# With authentication (recommended)
MCP_AUTH_TOKEN=your-secret-token npm start
The server will listen on http://localhost:4200/mcp (or your custom port).
Authentication (Optional):
You can secure the HTTP server with token-based authentication by setting the MCP_AUTH_TOKEN environment variable. If set, all requests must include the token in the Authorization header.
Example HTTP Request (with authentication):
curl -X POST http://localhost:4200/mcp \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-secret-token" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "list_containers",
"arguments": {
"all": true
}
}
}'
Development
Development Scripts
npm install
# Start HTTP server with auto-reload
npm run dev
# Start stdio server with auto-reload
npm run dev:stdio
# Build TypeScript to JavaScript
npm run build
Troubleshooting
Common Issues
1. Docker not running
Error: connect ENOENT /var/run/docker.sock
Solution: Start Docker Desktop or the Docker daemon.
2. Docker permission denied
Error: permission denied while trying to connect to the Docker daemon socket
Solution: On Linux, add your user to the docker group: sudo usermod -aG docker $USER (then log out and back in).
3. Node.js version too old
Error: Node.js 18 or higher required
Solution: Update Node.js to version 18 or higher.
4. Container not found
Error: No such container: xyz
Solution: Verify the container ID or name with list_containers.
5. Port already in use (HTTP mode)
Error: listen EADDRINUSE: address already in use :::4200
Solution: Change the port with PORT=3001 npm start
Debug Logging
For stdio mode, logs are written to stderr and appear in Claude Code logs:
- macOS:
~/Library/Logs/Claude/mcp-server-container-exec-mcp.log - Linux:
~/.config/Claude/logs/mcp-server-container-exec-mcp.log
For HTTP mode, logs appear in the terminal where you started the server.
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes
- Run
npm run buildto ensure it compiles - Test your changes
- Submit a pull request
License
MIT
Acknowledgments
Built with:
- Dockerode - Docker API client
- Model Context Protocol SDK - MCP implementation
- Zod - Schema validation
- Express - HTTP server
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。