system-command-mcp
Allows executing Bun commands (e.g., running scripts) via the system_exec tool.
Allows running Git commands (e.g., status, commit, diff) via the system_exec tool.
Allows executing Node.js scripts and commands via the system_exec tool.
Allows running npm commands (e.g., install, run scripts) via the system_exec tool.
Allows running pnpm commands (e.g., install, run scripts) via the system_exec tool.
Allows executing Python scripts and commands via the system_exec tool.
Allows running Yarn commands (e.g., install, run scripts) via the system_exec tool.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@system-command-mcpshow me the current git status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
system-command-mcp
跨平台系统命令 MCP Server。AI 使用稳定的 program + args[] 接口调用已注册程序,不需要选择 Bash、PowerShell 或 cmd.exe,也不需要用 which、where、command -v、Get-Command 探测工具。
工具
system_exec
program 枚举在 Server 启动时根据当前 PATH 自动生成:
{
"program": "git",
"args": ["status", "--short"],
"cwd": ".",
"timeoutMs": 30000
}参数不会经过 Shell 展开,$HOME、*.ts、&& 等会原样传递。
system_environment
返回平台、架构、根工作目录,以及逻辑程序名到真实可执行文件的映射。通常无需先调用;system_exec.program 的 Schema 已包含可用程序。
Related MCP server: SSH MCP Server
构建和测试
npm install
npm run build
npm test需要 Node.js 20 或更高版本。
MCP 配置
{
"mcpServers": {
"system-command": {
"command": "node",
"args": [
"/absolute/path/system-command-mcp/dist/src/cli.js",
"--root",
"/absolute/path/to/workspace"
]
}
}
}默认逻辑程序名
git、node、npm、pnpm、yarn、bun
python:依次解析 python3、python
ripgrep:解析 rg
powershell:依次解析 pwsh、powershell
只暴露当前环境实际存在的程序。
当前限制
仅支持 stdio transport;
不支持管道、重定向、任意 Shell 脚本、交互式 TTY 或后台常驻进程;
默认超时 30 秒,stdout/stderr 分别保留最后 1 MiB;
cwd 必须位于 --root 内;
程序快照在启动时生成,环境变化后需重启 Server;
超时和取消只保证终止直接子进程,不保证清理完整进程树。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Flicense-qualityDmaintenanceProvides safe shell command execution capabilities for AI agents and tools like VS Code Copilot through a whitelist-based filtering system.
- MIT
- Alicense-qualityCmaintenanceEnables AI agents to launch and manage system processes with strict security controls through executable allowlists, resource monitoring, and output capture capabilities.761MIT
- Flicense-qualityDmaintenanceEnables safe execution of terminal commands across different shells (bash, cmd, PowerShell) with configurable timeouts, working directories, and resource limits for command-line operations through AI assistants.
Related MCP Connectors
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Runtime permission, approval, and audit layer for AI agent tool execution.
Intent execution engine for autonomous agent task routing
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ubbcou/system-command-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server