SuperAPI AI Directory
Partner with us中文AI newsFavorites
All toolsAI agentscmd-mcp-server

cmd-mcp-server

CMD-MCP-Server is a server implementation based on the Model Context Protocol (MCP), used to execute CMD commands on Windows and Linux systems, and supports SSH connections. It allows command-line operations to be integrated with MCP-compatible applications (such as Claude), thereby extending agent capabilities. The project is written in TypeScript, based on the official MCP SDK, and has cross-platform compatibility. It can be automatically installed to Claude Desktop via Smithery, or installed manually (requires Node.js v16+ and npm/yarn). The server can be configured through environment variables or a configuration object. The project uses the MIT license. Note: executing command-line operations may pose risks, and security measures and input validation must be implemented in production environments.

Open website

About this tool

CMD-MCP-Server is a Model Context Protocol (MCP) server implementation. Its main purpose is to execute CMD commands, and it supports Windows and Linux systems as well as SSH connections. It can integrate command-line operations with MCP-compatible applications, for example hooking into Claude to provide additional agentic capabilities.

Main capabilities include: executing CMD commands through MCP; implemented in TypeScript; built on the official MCP SDK; cross-platform compatibility.

Usage:

  • Automatically install to Claude Desktop via Smithery.
  • Manual installation: requires Node.js (v16 or higher recommended) and the npm or yarn package manager.
  • Development environment setup: clone the repository, install dependencies, build the project. Build commands include npm run build(compiles TypeScript to JavaScript) and npm run prepare(prepares the release package).
  • The server can be configured through environment variables or a configuration object.

Dependencies include:@modelcontextprotocol/sdk ^1.0.1、glob ^10.3.10、zod-to-json-schema ^3.23.5.

Applicable scenarios: scenarios that require integrating command-line operations into MCP-compatible applications (such as Claude), used to extend agent capabilities.

Limitations and precautions: executing command-line operations may be potentially dangerous. When used in production environments, appropriate security measures and input validation must be implemented. The project uses the MIT license. Contributions and issue feedback can be made through GitHub.

Related tools

Browse category