MCP Mac Control

Name: MCP Mac Control
Author: dockndevai

作者：dockndevai版本 0.3.1i★ –i在你的电脑上运行

注册名称io.github.dockndevai/mcp-mac-control

安装

概览

作者提供的说明（英文原文）

Full macOS control — drive a Mac like a human: shell, AppleScript, files, and human-like GUI.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 其他

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： MACCTL_SAFE_MODE, MACCTL_MODE, MACCTL_CONFIRM, MACCTL_PATH_ALLOWLIST, MACCTL_PROTECTED_PATHS

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "mac-control": {
      "command": "npx",
      "args": [
        "-y",
        "@dockndevai/mcp-mac-control"
      ],
      "env": {
        "MACCTL_SAFE_MODE": "your-value",
        "MACCTL_MODE": "your-value",
        "MACCTL_CONFIRM": "your-value",
        "MACCTL_PATH_ALLOWLIST": "your-value",
        "MACCTL_PROTECTED_PATHS": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add mac-control --env MACCTL_SAFE_MODE=your-value --env MACCTL_MODE=your-value --env MACCTL_CONFIRM=your-value --env MACCTL_PATH_ALLOWLIST=your-value --env MACCTL_PROTECTED_PATHS=your-value -- npx -y @dockndevai/mcp-mac-control

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "mac-control": {
      "command": "npx",
      "args": [
        "-y",
        "@dockndevai/mcp-mac-control"
      ],
      "env": {
        "MACCTL_SAFE_MODE": "your-value",
        "MACCTL_MODE": "your-value",
        "MACCTL_CONFIRM": "your-value",
        "MACCTL_PATH_ALLOWLIST": "your-value",
        "MACCTL_PROTECTED_PATHS": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "mac-control": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@dockndevai/mcp-mac-control"
      ],
      "env": {
        "MACCTL_SAFE_MODE": "your-value",
        "MACCTL_MODE": "your-value",
        "MACCTL_CONFIRM": "your-value",
        "MACCTL_PATH_ALLOWLIST": "your-value",
        "MACCTL_PROTECTED_PATHS": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

MACCTL_SAFE_MODE env
Set true to invert to safe-by-default: read-only, all powers gated, confirmations on. Default false (full control).
MACCTL_MODE env
Access mode: read-only | read-write | admin. Defaults to admin (or read-only in safe mode).
MACCTL_CONFIRM env
Set true to require human approval (via MCP elicitation) on destructive ops. Default off in full control.
MACCTL_PATH_ALLOWLIST env
Comma-separated path roots the agent may touch (empty = anywhere).
MACCTL_PROTECTED_PATHS env
Comma-separated path roots that may be read but never modified/deleted (empty by default in full control).

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 dockndevai 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32606 个服务器的 0%
发布到注册中心的时间比此分类中其他 32606 个服务器的 49% 更新
基础检查结果等于或优于此分类中其他 32606 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

MCP Mac Control 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.3.1）于41天前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, Georgia MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211前天更新

安装

Georgia MCP

作者：abgeo

An MCP server for Georgian public data, read from the organizations that publish it.

电脑或云端今天更新

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

mcp-mac-control

A Model Context Protocol server that gives an AI agent full control of a Mac — like a person sitting at it. Shell, AppleScript, files, processes, and human-like GUI control: move, click, double/right-click, drag, scroll, type, and press key combos — with a screenshot + window/screen-size perception loop.

⚠️ This server is full-control by default. It starts in admin mode with command execution, deletes, and GUI input all enabled. That is powerful and dangerous: anything the agent reads (a web page, an email, a file) could contain a prompt injection that then runs arbitrary code on your Mac. Only connect it to an agent and content you trust. Set `MACCTL_SAFE_MODE=true` to flip the whole thing to safe-by-default. If you want safe-by-default as the baseline, use the sibling @dockndevai/mcp-macos instead.

Part of the dockndevai MCP server suite.

What it gives an agent (26 tools)

Perceive — screenshot, get_screen_size, list_windows, get_frontmost_app, list_apps, system_info, list_directory, read_file, list_processes, get_clipboard

Operate the desktop like a human — move_mouse, click (left/right/double), drag, scroll, type_text, key_press (with ⌘/⌥/⌃/⇧), activate_app, quit_app, open, set_clipboard, notify, write_file

Full power — run_command (any program, no shell unless you ask for one), run_applescript (AppleScript/JXA — drive any scriptable app), delete_path (→ Trash), kill_process

The classic loop: screenshot → decide → click/type/drag/scroll → screenshot again.

Install

npx -y @dockndevai/mcp-mac-control

macOS only. You'll need to grant the host app (Terminal, your IDE, Claude Desktop, …) macOS permissions the first time each capability is used:

Screen Recording → for screenshot
Accessibility → for GUI input (click, type_text, drag, scroll, key_press) and list_windows
Automation → for AppleScript / app control
Mouse control uses cliclick: brew install cliclick

Configure (Claude Code)

claude mcp add mac-control -- npx -y @dockndevai/mcp-mac-control

That's it — it's full-control by default. To scope it down, add env flags (see below). See docs/CLIENTS.md for Claude Desktop / Cursor / Codex / VS Code / Windsurf, and .env.example for every variable.

Dialing the control up or down

Full control needs no configuration. Everything below is about restricting it:

Variable	Default	Effect
`MACCTL_SAFE_MODE`	`false`	`true` → read-only, every power gated, confirmations on (safe-by-default)
`MACCTL_MODE`	`admin`	`read-only` / `read-write` / `admin` — caps which tools are registered
`MACCTL_ALLOW_EXEC`	`true`	shell / AppleScript / kill
`MACCTL_ALLOW_DELETE`	`true`	delete to Trash
`MACCTL_ALLOW_INPUT`	`true`	GUI input (mouse/keyboard)
`MACCTL_CONFIRM`	`false`	`true` → destructive ops pause for human approval via MCP elicitation
`MACCTL_PATH_ALLOWLIST`	(empty = anywhere)	confine file ops to these roots
`MACCTL_PROTECTED_PATHS`	(empty)	roots readable but never modified/deleted
`MACCTL_COMMAND_ALLOWLIST`	(empty = any)	restrict `run_command` to these programs
`MACCTL_DRY_RUN`	`false`	validate + log writes without executing
`MACCTL_AUDIT_LOG`	`true`	JSON audit line per guarded op, to stderr

The policy engine (src/security.ts) is the same graduated model as the rest of the suite — this server just ships it wide open by default. See SECURITY.md.

AI risk guard (optional)

For an extra layer on top of the static rules, this server can consult a local laya-guard daemon before running a high-risk tool (run_command, run_applescript, delete_path). The guard classifies the actual command — deterministic patterns plus a local decision model — as allow / confirm / block. It runs *after* the deterministic policy and can only tighten (add a confirm or block), never grant.

Variable	Default	Effect
`MACCTL_GUARD_MODE`	`off`	`monitor` (log what it would do) / `enforce` (block or require confirm)
`MACCTL_GUARD_URL`	`http://127.0.0.1:8799`	the local laya-guard daemon
`MACCTL_GUARD_TIMEOUT_MS`	`2000`	per-check timeout
`MACCTL_GUARD_FAIL_CLOSED`	`confirm`	when the daemon is unreachable in enforce mode: `confirm` or `allow`

Run the daemon with pipx install laya-guard && laya-guard. Start in monitor to see what it catches, then switch to enforce.

Developing

npm install

npm run build echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node dist/index.js # list tools npm test

Licence

MIT