What is the main purpose of Shell Mcp Server?
It lets MCP clients execute shell commands safely, supporting different terminal environments like cmd and PowerShell.
@ZHAN2006
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"shell-mcp-server": {
"command": "npx",
"args": [
"-y",
"shell-mcp-server"
]
}
}
}在服务端操作系统中执行Shell命令,支持不同终端类型。可用于文件操作、系统信息查询、程序运行等场景。注意:具有潜在安全风险,应限制敏感命令执行。
Shell Mcp Server is an MCP (Model Context Protocol) server that allows you to execute shell commands. It supports multiple terminal types (cmd, PowerShell) and is built on the MCP SDK. Designed for developers and AI agents needing command execution via the MCP protocol.
You can run it directly with npx -y shell-mcp-server, install it globally (npm install -g shell-mcp-server and run shell-mcp-server), or add it as a project dependency. For MCP client configuration, use the provided JSON to point to the server. Programmatically, import startServer and call it with options like port.
It lets MCP clients execute shell commands safely, supporting different terminal environments like cmd and PowerShell.
No, because it is distributed via npm and runs on Node.js. You need Node.js to run `npx` or to install the package.
Add the following JSON to your `mcpServers` configuration: ```json { "mcpServers": { "shell-mcp-server": { "command": "npx", "args": ["-y", "shell-mcp-server"] } } } ```
The README does not specify the transport; it simply uses the MCP SDK’s default server setup.
The README only states “safe execution of shell commands” but provides no details on restrictions or sandboxing.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Compliance frameworks delivered to AI agents. Nizh gives your agent read access to your organization's compliance program — SOC 2, ISO 27001, CMMC 2.0, NIST, and more — as MCP tools, so it can check posture, read a contr
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
评论