Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器clawhub未标认证来源可访问clear审计提醒

mac-compute-useMac 计算使用

Agent Skill

mac-compute-use 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

21,720

周安装

933

GitHub Stars

1

下载量

7,613
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:mac-compute-use(Mac 计算使用)
来源仓库:https://github.com/reg2005/mac-compute-use
安装命令:
openclaw skills install mac-compute-use
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install mac-compute-use

简介

通过 Accessibility API 控制 macOS 应用程序界面交互。

  • 适用于自动化操作、UI 测试等研究检索类任务。
  • 可打开应用、点击按钮、输入文本并读取界面状态。
  • 必须授予辅助功能权限,存在安全风险需谨慎授权。
  • 仅支持图形界面应用,命令行工具无法直接控制。mac-compute-use 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
mac-compute-use
description
Control macOS applications via Accessibility API through an MCP server. Open apps, click buttons, type text, press keys, scroll, and read UI state. Use when: (1) interacting with native macOS apps (Finder, Messages, Mail, etc.), (2) automating GUI workflows — clicking, typing, navigating menus, (3) reading screen content or UI state from any app, (4) controlling browsers for web automation without browser extensions, (5) any task requiring 'computer use' or 'desktop control' on macOS. NOT for: Linux/Windows, headless servers, or tasks achievable via CLI/API without GUI.
homepage
https://github.com/mediar-ai/mcp-server-macos-use
metadata

Mac Compute Use

Control macOS GUI through the Accessibility API via MCP.

Setup

  1. Install the MCP server:
brew tap reedburns/mcp-server-macos-use
brew install mcp-server-macos-use
  1. Register with mcporter:
mcporter config add macos-use --transport stdio --command $(which mcp-server-macos-use)
  1. Grant Accessibility permission:

System Settings → Privacy & Security → Accessibility → add mcp-server-macos-use

  1. Verify:
mcporter list macos-use --schema

Tools

All tools are called via mcporter call macos-use.<tool> key=value.

open_application_and_traverse

Open/activate an app and get its UI tree.

mcporter call macos-use.macos-use_open_application_and_traverse identifier="Google Chrome"
mcporter call macos-use.macos-use_open_application_and_traverse identifier="com.apple.finder"
mcporter call macos-use.macos-use_open_application_and_traverse identifier="TextEdit"

Returns: PID, element count, visible interactive elements, and a JSON file path with full UI tree.

click_and_traverse

Click at coordinates (from UI tree) and get updated state.

mcporter call macos-use.macos-use_click_and_traverse pid=408 x=701 y=73 width=102 height=41
  • x, y: top-left corner of the element (from traversal)
  • width, height: optional, when provided click lands at center

type_and_traverse

Type text into the focused app.

mcporter call macos-use.macos-use_type_and_traverse pid=408 text="Hello world"

press_key_and_traverse

Press a key with optional modifiers.

mcporter call macos-use.macos-use_press_key_and_traverse pid=408 keyName=Return
mcporter call macos-use.macos-use_press_key_and_traverse pid=408 keyName=a modifierFlags='["Command"]'
mcporter call macos-use.macos-use_press_key_and_traverse pid=408 keyName=Tab
mcporter call macos-use.macos-use_press_key_and_traverse pid=408 keyName=Escape

Valid modifiers: CapsLock, Shift, Control, Option, Command, Function, NumericPad, Help.

scroll_and_traverse

Scroll within an app window.

mcporter call macos-use.macos-use_scroll_and_traverse pid=408 x=500 y=400 deltaY=3
mcporter call macos-use.macos-use_scroll_and_traverse pid=408 x=500 y=400 deltaY=-3
  • deltaY positive = scroll down, negative = scroll up
  • deltaX optional, for horizontal scroll

refresh_traversal

Get current UI state without performing any action.

mcporter call macos-use.macos-use_refresh_traversal pid=408

Workflow Pattern

Typical automation flow:

  1. Open app → get PID and visible elements
  2. Read the visible_elements in the response summary — these are interactive elements with coordinates
  3. Click/type/press using coordinates from the UI tree
  4. Read the response — it shows what changed (diff) and new visible elements
  5. Repeat until task is complete

Reading the Response

Each tool returns a compact summary with:

  • status: success/error
  • pid: process ID (use for subsequent calls)
  • file: path to full JSON with all elements (use grep or python3 to search)
  • visible_elements: key interactive elements currently visible, with coordinates

When you need to find a specific element, grep the JSON file:

grep -i "search text" /tmp/macos-use/<file>.json

Or parse with Python:

python3 -c "
import json
with open('/tmp/macos-use/<file>.json') as f:
    data = json.load(f)
for e in data.get('traversal',{}).get('elements',[]):
    text = (e.get('text') or '').strip()
    if text and 'search' in text.lower():
        print(f'[{e[\"role\"]}] ({e[\"x\"]},{e[\"y\"]} {e.get(\"width\",\"?\")}x{e.get(\"height\",\"?\")}) {text}')
"

Tips

  • Always use --output json for machine-readable results when chaining commands
  • After clicking, wait a moment then refresh_traversal if the UI didn't update in the diff
  • Use app name ("Google Chrome"), bundle ID ("com.google.Chrome"), or path to open apps
  • Coordinates are absolute screen positions — if the window moves, refresh the traversal
  • The server writes traversal JSON to /tmp/macos-use/ — these files are temporary

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

92.49%
按下载量换算7,041

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills