MCP Shell Server
A simple MCP server that provides a terminal tool for executing shell commands with safety features like timeouts and error handling.
README
MCP Shell Server
A simple Model Context Protocol (MCP) server that exposes a terminal tool for executing shell commands.
Features
- Terminal Tool: Execute shell commands and get results
- Safety Features: 30-second timeout and error handling
- Flexible: Optional working directory parameter
- Claude Integration: Tool named
run_commandfor easy Claude integration
Installation
The project uses uv for dependency management. Dependencies are already configured in pyproject.toml.
Usage
Running the Server
# Using uv
uv run python server.py
# Or directly with Python
python server.py
The server will start and wait for MCP client connections via stdin/stdout.
Tool Description
The server exposes a run_command tool with the following parameters:
command(required): The shell command to executeworking_directory(optional): Directory to run the command in
Example Usage
The terminal tool can be used to run commands like:
ls -la- List files in current directorypwd- Get current working directoryecho "Hello World"- Print textpython --version- Check Python version
Response Format
The tool returns a dictionary with:
stdout: Standard output from the commandstderr: Standard error from the commandreturn_code: Exit code of the commandsuccess: Boolean indicating if command succeeded (return code 0)
MCP Integration
This server follows the Model Context Protocol specification and can be integrated with MCP clients like Claude Desktop. The tool is named run_command for easy identification and use.
Security Note
This server allows execution of arbitrary shell commands. Use with caution and ensure proper access controls are in place in production environments.
Development
This is a simple implementation using the MCP Python SDK with FastMCP. The server can be extended with additional tools as needed.
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。