What commands are blocked for security?
The server prevents execution of potentially harmful commands like `rm -rf`, `sudo`, and others that could compromise system integrity.
Command Execution MCP Server for Claude Desktop
@ryaker
基本信息
关于 Command Execution MCP Server for Claude Desktop
Command Execution MCP Server for Claude Desktop
Command Execution MCP Server for Claude Desktop 配置
Command Execution MCP Server for Claude Desktop 工具
工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Command Execution MCP Server for Claude Desktop?
The Command Execution MCP Server is a secure, controlled tool that allows Claude to execute shell commands directly on your local system. It provides safe and flexible command-line interaction through Claude's interface, with built-in safety checks and cross-platform support for macOS and other Unix-like systems.
How to use Command Execution MCP Server for Claude Desktop?
Install Node.js (v16+), npm, and Claude Desktop. Navigate to the server directory and run npm install @modelcontextprotocol/sdk. Add the provided configuration block to your Claude Desktop configuration file (claude_desktop_config.json), specifying the correct path to the script. Use the execute-command tool with a command string and optional working directory, e.g., execute-command with command="ls -la" and workingDirectory="/Users/yourusername/Documents".
Key features of Command Execution MCP Server for Claude Desktop
- Secure command execution with built-in safety checks
- Working directory support for controlled execution
- Cross-platform compatibility (macOS and Unix-like systems)
- Extensive error handling with detailed feedback
- Timeout (30s) and buffer (1MB) limits to prevent runaway commands
- Dangerous command blocking (e.g.,
rm -rf,sudo)
Use cases of Command Execution MCP Server for Claude Desktop
- Run file operations like listing contents in a specific directory
- Execute system information commands (e.g.,
uname,df -h) - Perform development tasks such as compiling code or running scripts
- Automate command-line workflows through Claude's natural language interface
常见问题
What are the execution constraints?
Maximum execution time is 30 seconds, maximum output buffer is 1MB, and the working directory must be valid. Interactive commands are not supported.
What are the runtime dependencies?
Node.js v16 or later and npm are required. The server uses the `@modelcontextprotocol/sdk` package and runs via the Node.js runtime.
Where does command output go?
Output is returned directly to Claude within the 1MB limit, with detailed feedback on execution results and errors. All data stays on your local machine.
AI 与智能体 分类下的更多 MCP 服务器
Nova Data Analytics
nova-data-analyticsAmazon Seller Central MCP server. Connect Seller Central, Vendor Central and Amazon Ads to Claude, ChatGPT, Gemini or Cursor, and ask for net profit per SKU with your own COGS, VAT and FBM shipping costs, PPC down to the
Hostinger
hostingerModel Context Protocol (MCP) server for Hostinger API. If you don't want to install or run anything locally, connect directly to Hostinger's hosted MCP server: This opens a browser window to authorize via OAuth. Once app
148
Atwork
Atwork TeamConnect Atwork to Claude, ChatGPT, Cursor or any MCP client and work with your real data: ask what is overdue, total a sheet by any field, add tasks, update rows, post comments and draft pages. The assistant acts as you
TruVerifAI Panel-review
TruVerifAITruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g
1
Gemina
Gemina Tech Ltd.Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in (OAuth 2.1) or API key, free FileTag tier, data residency in the EU, US, Israel or Asia.
评论