
Peekaboo
MCPmacOS screen capture, accessibility-tree inspection and native UI automation, served over MCP so agents can see the screen and click, type and operate menus. Requires macOS 15+ with Screen Recording and Accessibility permissions granted.
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 openclaw/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 4.9.4
Peekaboo 4.9.4 is a fix release. While a granted Peekaboo.app is running, commands no longer drop to the permissions of an on-demand daemon started from an ungranted terminal, permission guidance names macOS 27's renamed "Device Control and Data Access" Settings row, and an unsigned source build such as Homebrew core's peekaboo formula now explains why Bridge and daemon hosts reject it and points to the notarized install. See the changelog for details.
Automate an app
List Safari's windows, copy the intended window_id (12345 below), then keep the entire interaction pinned to
that exact window:
peekaboo window list --app Safari --json
peekaboo click "Address and search bar" --app Safari --window-id 12345
peekaboo type "github.com/openclaw/Peekaboo" --app Safari --window-id 12345
peekaboo press Return --app Safari --window-id 12345
Targeted semantic and typed CLI input uses background delivery when Peekaboo can resolve the process, so the app does
not have to become frontmost. Raw CLI press chords can also stay background with an exact window selector. The CLI
also accepts a fresh exact non-dialog snapshot; that snapshot is required by background-only Agent/MCP policy.
App/PID-only and targetless chords require explicit foreground consent, as do window-selector-only Agent/MCP chords.
Prefer a semantic action such as menu click when one exists. 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" --allow-foreground
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
- Project direction
- Platform support
- Architecture
- Building from source
- Testing
- Agent chat loop
- Command reference
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.
Ressources associées

Peekaboo
CLImacOS screenshot and UI automation CLI: capture the screen, read the accessibility tree for structured UI elements, then click, type, and switch windows and menus. Also runs as an MCP server for Claude Code and Codex. Needs macOS 15+ with Screen Recording and Accessibility permissions.
openclaw/Peekaboo5.3k
Windows-MCP
MCPLets agents operate the Windows desktop directly: launch apps, switch windows, simulate keyboard and mouse, read UI elements and run PowerShell, without needing a vision model. Windows only.
CursorTouch/Windows-MCP9.3k
Build macOS Apps
PluginOpenAI's official Codex plugin for macOS apps: building and running, SwiftUI scenes and AppKit interop, testing and troubleshooting, signing, notarization and packaging, and logging instrumentation. Requires macOS and Xcode; Codex only.
openai/plugins7.5k
Mole
CLImacOS cleanup and maintenance CLI (mo): clears caches and logs, fully uninstalls apps, analyzes disk usage, removes project build artifacts and shows system status. Preview deletions with --dry-run; disk analysis and status support JSON output. Needs macOS 12+.
tw93/Mole70.6k
Midscene Skills
SkillCross-platform UI automation skills built on Midscene.js visual recognition: control browsers, desktops, Android, iOS and HarmonyOS devices in natural language, and set up Vitest + Midscene E2E tests. Bring your own vision model API key; maintained by the Midscene team.
web-infra-dev/midscene-skills318
WPS Skills
MCPLets agents operate WPS Office Writer, Spreadsheets and Presentation on your computer through 200+ MCP tools covering formulas, pivot tables, charts, comments, slide styling and animation. Requires WPS; clone, build from source and install the WPS add-in. Runs on macOS, Windows and Linux.
lc2panda/wps-skills652