自动化中等风险

Peekaboo(macOS 屏幕自动化与 MCP 工具)

Peekaboo 是一款 macOS 命令行工具与可选 MCP 服务器,面向 AI Agent 提供屏幕截图、UI 可访问性检查与原生 UI 自动化能力,支持本地或远程视觉问答模型。

by @openclawv1.0.07 浏览3 下载
#agent#cli#macOS#mcp#Node.js#Swift#UI自动化
推荐方式

直接交给 AI

无需安装文件。复制一句话,让 AI 在线读取这个 Skill。

下载 Skill ZIP ↓ 查看 SKILL.md 原文 ↗
01

它能帮你做什么

先看懂,再决定要不要交给 AI。

Peekaboo 是一个面向 macOS 15+ 的开源项目(MIT 协议),由 steipete 维护,包含 CLI、菜单栏应用以及可被外部 MCP 客户端加载的 MCP 服务器。它让 AI Agent 能够:1) 通过 `image`/`screen` 命令对指定应用或整个屏幕进行截图;2) 通过 `see`/`list` 命令获取窗口与 UI 元素的结构化可访问性快照(含不透明元素 ID);3) 通过 `click`/`type`/`press`/`scroll`/`drag`/`set-value`/`perform-action` 等命令进行原生 UI 自动化;4) 通过 `agent` 子命令让模型在自然语言层面规划多步操作;5) 通过 `mcp` 子命令将上述工具集暴露给 Codex、Claude Code、Cursor 等 MCP 客户端。视觉问答可对接托管、兼容或本地模型后端;凭据与配置存放在 ~/.peekaboo。项目还提供 zsh/bash/fish shell 补全、Homebrew tap、npm 包(@steipete/peekaboo,需 Node.js 22+)以及签名 DMG 安装。注意:使用 Screen Recording、Accessibility 等 macOS 权限;后台投递输入时要求应用可被解析,否则需要 --foreground 才能在聚焦窗口中输入。

✓让 AI Agent 截取 macOS 屏幕或指定应用窗口
✓对运行中的应用进行 UI 元素可见性检查并获取结构化 ID
✓自动点击、键入、滚动、拖拽等 UI 交互任务
✓通过自然语言让 Agent 自动完成多步桌面操作(如打开 Safari、访问网址、搜索)
✓将 Peekaboo 工具集作为 MCP server 接入 Claude Code、Cursor、Codex 等客户端
✓运行脚本化的 macOS 自动化工作流
02

怎么交给 AI

在线读取优先,本地安装作为备选。

◎
在线读取推荐 · 不需要安装

适合能访问网页的 ChatGPT、Agent 或其他 AI。

AI Prompt请访问 https://skills.dhmip.cn/skills/openclaw/peekaboo/SKILL.md,读取并按照该 Skill 完成任务;如当前环境支持本地安装,也可以下载该 Skill。
↓
下载安装到 Agent适合支持 Skills 的客户端

未登录时可使用公共安装文档;登录后可以按不同 AI 分开管理。

Install Prompt请根据 https://skills.dhmip.cn/install/skillhub.md,安装 @openclaw/peekaboo。
登录后管理多个 AI →
03

兼容性与要求

安装或使用前,先确认环境是否匹配。

适用客户端

MCP 兼容客户端(Claude Code、CodeX、Cursor 等)macOS CLI 直连macOS 菜单栏应用Homebrewnpm/Node.js 22+ 环境

使用要求

  • macOS 15 或更高版本
  • Swift 6.2+(源码构建)
  • Node.js 22+(使用 npm 包及子命令)
  • Homebrew(可选,用于 CLI 安装)
  • macOS Screen Recording 权限(截图必需)
  • macOS Accessibility 权限(UI 检视与控制必需)
  • macOS 合成输入所需权限(依场景)
  • 可配置的大模型 Provider(用于 Agent 与视觉问答)
⌘技术详情查看完整 SKILL.md 与原始内容
⌄
SKILL.mdRaw ↗

Imported Skill

该内容由 Skills导航从来源页面解析重建,可能不包含完整附件,请核对原始来源。

GitHub - openclaw/Peekaboo: Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models. · GitHub

Skip to content

Navigation Menu

Sign inAppearance settings

PlatformAI CODE CREATIONGitHub CopilotWrite better code with AI
GitHub Copilot appDirect agents from issue to merge
MCP RegistryIntegrate external tools

DEVELOPER WORKFLOWSActionsAutomate any workflow
CodespacesInstant dev environments
IssuesPlan and track work
Code ReviewManage code changes
Code QualityEnforce quality at merge

APPLICATION SECURITYGitHub Advanced SecurityFind and fix vulnerabilities
Code securitySecure your code as you build
Secret protectionStop leaks before they start

EXPLOREWhy GitHub
Documentation
Blog
Changelog
Marketplace

View all features

SolutionsBY COMPANY SIZEEnterprises
Small and medium teams
Startups
Nonprofits

BY USE CASEApp Modernization
DevSecOps
DevOps
CI/CD
View all use cases

BY INDUSTRYHealthcare
Financial services
Manufacturing
Government
View all industries

View all solutions

ResourcesEXPLORE BY TOPICAI
Software Development
DevOps
Security
View all topics

EXPLORE BY TYPECustomer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills

SUPPORT & SERVICESDocumentation
Customer support
Community forum
Trust center
Partners

View all resources

Open SourceCOMMUNITYGitHub SponsorsFund open source developers

PROGRAMSSecurity Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program

REPOSITORIESTopics
Trending
Collections

EnterpriseENTERPRISE SOLUTIONSEnterprise platformAI-powered developer platform

AVAILABLE ADD-ONSGitHub Advanced SecurityEnterprise-grade security features
Copilot for BusinessEnterprise-grade AI features
Premium SupportEnterprise-grade 24/7 support

Pricing
Type / to search

Sign in
Sign upAppearance settings

You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

Uh oh!

There was an error while loading. Please reload this page.

openclaw

/

Peekaboo

Public

Notifications
You must be signed in to change notification settings

Fork
383

Star
5k

Code

Issues
0

Pull requests
0

Actions

Projects

Security and quality
0

Insights

Additional navigation options

Code

Issues

Pull requests

Actions

Projects

Security and quality

Insights

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files
NameNameLast commit message
Last commit date
Latest commit
 

History
3,071 Commits
3,071 Commits

.agents/skills

.agents/skills

 
 

.github

.github

 
 

AXorcist @ dbafbe3

AXorcist @ dbafbe3

 
 

Apps

Apps

 
 

Commander @ 0cef08a

Commander @ 0cef08a

 
 

Core

Core

 
 

Examples

Examples

 
 

Helpers/MenuBarHelper

Helpers/MenuBarHelper

 
 

Swiftdansi @ 62adad4

Swiftdansi @ 62adad4

 
 

Tachikoma @ 2ba00c8

Tachikoma @ 2ba00c8

 
 

TauTUI @ 91eebd2

TauTUI @ 91eebd2

 
 

assets

assets

 
 

docs

docs

 
 

experiments/cgs-menu-probe

experiments/cgs-menu-probe

 
 

homebrew

homebrew

 
 

release

release

 
 

scripts

scripts

 
 

skills/peekaboo

skills/peekaboo

 
 

tests

tests

 
 

.crabbox.yaml

.crabbox.yaml

 
 

.envrc

.envrc

 
 

.gitignore

.gitignore

 
 

.gitmodules

.gitmodules

 
 

.mac-release.env

.mac-release.env

 
 

.npmignore

.npmignore

 
 

.swiftformat

.swiftformat

 
 

.swiftlint-ci.yml

.swiftlint-ci.yml

 
 

.swiftlint.yml

.swiftlint.yml

 
 

AGENTS.md

AGENTS.md

 
 

CHANGELOG.md

CHANGELOG.md

 
 

CLAUDE.md

CLAUDE.md

 
 

LICENSE

LICENSE

 
 

Package.swift

Package.swift

 
 

README.md

README.md

 
 

VISION.md

VISION.md

 
 

appcast.xml

appcast.xml

 
 

package.json

package.json

 
 

peekaboo-mcp.js

peekaboo-mcp.js

 
 

pnpm-lock.yaml

pnpm-lock.yaml

 
 

pnpm-workspace.yaml

pnpm-workspace.yaml

 
 

version.json

version.json

 
 

View all files

Repository files navigation

README
MIT license
Security

More items

Peekaboo 🫣 — Mac automation that sees the screen and does the clicks.

Peekaboo is a macOS CLI and menu-bar app for screen capture, accessibility inspection, and native UI automation. Use it directly, let its agent plan multi-step work, or expose the same toolset to MCP clients.

Install

The released CLI and app require macOS 15 or later.

CLI with Homebrew

brew install steipete/tap/peekaboo

MCP package with npm

The npm package requires Node.js 22 or later and includes the CLI plus its MCP launcher.

npx -y @steipete/peekaboo --version

See MCP setup to connect it to Codex, Claude Code, Cursor, or another MCP client.

Mac app

Download the signed DMG from the latest GitHub release. The menu-bar app provides permission onboarding, visual feedback, and agent sessions; install the CLI separately when you also need peekaboo on PATH.

For source builds and alternative install details, see the installation guide.

Quick start

Check the permissions available to Peekaboo, then take a screenshot:

peekaboo permissions status
peekaboo image --mode screen --path /tmp/peekaboo-screen.png

Screen capture requires Screen Recording permission. Accessibility permission enables UI inspection and control; the permissions guide covers setup and the additional permission used for synthetic input.

Inspect a running app to get a structured UI map with opaque element IDs:

peekaboo see --app Finder --json

That is the core loop: observe the current screen, choose an element from the result, and act on it.

Automate an app

Target an element by its accessible label, then send text to the same app:

peekaboo click "Address and search bar" --app Safari
peekaboo type "github.com/openclaw/Peekaboo" --app Safari --return

Targeted input uses background delivery when Peekaboo can resolve the process, so the app does not have to become frontmost. Add --foreground when an app only accepts input in its focused key window. See the automation guide for element IDs, coordinates, snapshots, waits, and input behavior.

Agent and MCP

The agent combines the same observation and action tools into a natural-language run:

peekaboo agent "Open Safari, go to github.com, and search for Peekaboo"

Agent runs need a configured model provider. See agent setup for providers and sessions, or MCP setup to expose Peekaboo's tools to another client.

Command map

Goal
Commands
Guide

Observe the desktop
image, see, list, screen
Capture and inspection

Interact with UI
click, type, press, scroll, drag, set-value, perform-action
Automation

Control macOS
app, window, menu, menubar, dock, dialog, space
Command reference

Run workflows
agent, run
Agent · Scripts

Integrate with clients
mcp, browser, tools
MCP

Run peekaboo help <command> for live CLI help. The complete command index links to flags, examples, and troubleshooting for every command.

Configuration

Peekaboo stores provider credentials and settings under ~/.peekaboo. Use peekaboo config to inspect or change them, and consult the configuration guide for profiles, environment variables, and custom providers. The provider reference covers hosted, compatible, and local model backends.

Shell completions for zsh, bash, and fish come from peekaboo completions; see the completion guide for persistent setup.

Learn more

Project direction

Platform support

Architecture

Building from source

Testing

Agent chat loop

Service API

Community

PeekabooWin — Windows-first rewrite of the Peekaboo automation loop (JavaScript + PowerShell) by @FelixKruger

PeekabooX — Linux-first rewrite of the Peekaboo automation loop (Rust + Python) by @nordbyte

Development

Source builds require macOS 15 or later, Swift 6.2 or later, Node.js 22 or later, and the repository's submodules.

pnpm install --frozen-lockfile
pnpm run build:cli
pnpm run lint:docs
pnpm run test:safe

More build, signing, and test details live in docs/building.md.

License

MIT. See LICENSE.

About
Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
www.peekaboo.boo
Topics
aimacosmcpscreenshotsswift
Resources
Readme
MIT license
Security policy
Security policy
Activity
Custom properties
Stars
5.0k stars
Watchers
14 watching
Forks
383 forks
Report repository

Releases

Used by

Contributors

Languages

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms

Privacy

Security

Status

Community

Docs

Contact

Manage cookies

Do not share my personal information

You can’t perform that action at this time.