Peekaboo

mcp
Guvenlik Denetimi
Basarisiz
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 4983 GitHub stars
Code Basarisiz
  • process.env — Environment variable access in .github/workflows/clawsweeper-dispatch.yml
  • fs module — File system access in .github/workflows/clawsweeper-dispatch.yml
  • rm -rf — Recursive force deletion command in .github/workflows/macos-ci.yml
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This tool is a macOS CLI and MCP server that provides AI agents with screen capture, visual analysis, and full GUI automation capabilities (clicking, typing, scrolling).

Security Assessment
Overall risk: Medium. The tool inherently requires access to highly sensitive data because it needs macOS Screen Recording and Accessibility permissions to function. It can literally see everything on your screen and control your computer's UI. While the automated audit found no hardcoded secrets and no explicitly dangerous permissions requested in the code, the tool does make network requests to send visual data to external AI providers (like OpenAI, Anthropic, or Google) for analysis. The two failed audit checks for `rm -rf` commands are false positives; they are safely located within GitHub Actions CI/CD workflows for cleaning up build environments, not in the core application code.

Quality Assessment
Overall quality is excellent. The project is highly active, with its last code push occurring today, and boasts strong community trust with over 3,200 GitHub stars. It is properly licensed under the permissive MIT license and is widely compatible with major AI CLIs and coding environments. The documentation is clear and comprehensive. Note that the current version 3 release is in beta, so users should expect minor bugs.

Verdict
Use with caution — while the code itself is safe and well-maintained, granting screen recording and UI control access to any tool requires careful consideration of your privacy boundaries and trust in your configured AI providers.
SUMMARY

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.

README.md

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

CI npm GitHub release macOS 15+ Swift 6.2 Node License Homebrew Ask DeepWiki

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.

Peekaboo banner

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 see --no-elements --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.

What's new in 4.0

Peekaboo 4 has an exact 33-command root surface, consistent duration and
coordinate grammar, native verify polling, and honest JSON effects after an action request has been
parsed and classified. Pre-dispatch argument parse/bind failures may omit effect. If you have
existing scripts or agent instructions, use the Peekaboo 4 migration guide
for the complete old-to-new command and flag map.

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
peekaboo press Return --app Safari --foreground

Targeted semantic and typed input uses background delivery when Peekaboo can resolve the process, so the app does not have to become frontmost. Raw press chords always require explicit --foreground; prefer a semantic action such as menu click in background workflows. 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 see, screen list, window list Capture and inspection
Interact with UI click, type, press, scroll, drag, set-value, action Automation
Control macOS app, window, menu, menubar, dock, dialog, space Command reference
Run workflows agent, capture Agent · Capture
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

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.

Yorumlar (0)

Sonuc bulunamadi