Mac Shell MCP Server
@cfdude
About Mac Shell MCP Server
An MCP (Model Context Protocol) server for executing macOS terminal commands with ZSH shell. This server provides a secure way to execute shell commands with built-in whitelisting and approval mechanisms.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mac-shell-mcp": {
"command": "node",
"args": [
"build/index.js"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Mac Shell MCP Server?
Mac Shell MCP Server is an MCP (Model Context Protocol) server for executing macOS terminal commands with ZSH shell. It provides a secure way to run shell commands with built-in whitelisting and approval mechanisms, designed for AI assistants like Roo Code and Claude Desktop.
How to use Mac Shell MCP Server?
Install by cloning the repository and running npm install && npm build, or use npx directly from the GitHub repository. Configure the server in your MCP client settings (Roo Code or Claude Desktop), then invoke tools such as execute_command or get_whitelist to run and manage shell commands.
Key features of Mac Shell MCP Server
- Execute macOS terminal commands through MCP
- Three security levels: safe, requires approval, forbidden
- Pre-configured whitelist with common safe commands
- Approval workflow for potentially dangerous commands
- Tools to manage whitelist and pending approvals
Use cases of Mac Shell MCP Server
- AI-assisted file browsing and directory listing
- Safe execution of read-only commands (ls, cat, grep)
- Controlled file operations with approval (cp, mv, mkdir)
- Blocking dangerous commands like rm and sudo
FAQ from Mac Shell MCP Server
What commands are safe by default?
Safe commands include ls, pwd, echo, cat, grep, find, cd, head, tail, and wc. These execute without approval.
What commands require approval?
Commands like mv, cp, mkdir, touch, chmod, and chown require explicit approval before execution.
What
Frequently asked questions
What commands are safe by default?
Safe commands include ls, pwd, echo, cat, grep, find, cd, head, tail, and wc. These execute without approval.
What commands require approval?
Commands like mv, cp, mkdir, touch, chmod, and chown require explicit approval before execution.
Basic information
More Developer Tools MCP servers
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
mcp-excalidraw
yctimlinMCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.
Unity MCP (Server + Plugin)
IvanMurzakAI Skills, MCP Tools, and CLI for Unity Engine. Full AI develop and test loop. Use cli for quick setup. Efficient token usage, advanced tools. Any C# method may be turned into a tool by a single line. Works with Claude Code, Gemini, Copilot, Cursor and any other absolutely for fr

discoverGPT
Joe MonastierodiscoverGPT is visualAI's unified MCP gateway for AI commerce, exposing 29 tools across four capabilities on one canonical product catalog: trimodal search (natural-language, precise-color, and image-similarity), AI cata

Moxie Docs
Jackalope-DevAutomated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.
Comments