Peekaboo

MCP.Pizza Chef: openclaw

This tool gives your AI assistant eyes and hands on your Mac: it can capture a picture of your whole screen or a single app window, read what's currently on screen as an organized list of buttons and text, and then click, type, or navigate menus for you. It connects to Cursor and other compatible apps such as Claude Code, and installs with one command using npx — no extra account or password is required to get started, though the optional automated 'agent' mode needs a connected AI model.

Coding

Other

Web/Research

Use This MCP server To

Take a screenshot of any app or my entire screen See exactly what's on my screen as a readable list Click a button or link inside an app for me Type text into a website or app automatically Open a browser, search a site, and click the results Automate a multi-step task on my Mac hands-free

README

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

macOS 15+ License

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.

Peekaboo FAQ

Can I use this to take a screenshot of a specific app?

Yes — you can ask your AI assistant to capture just one app's window or your entire screen and save the image.

Can I use this to have my AI click buttons and fill out forms on my Mac?

Yes — it can find buttons, links, and text fields inside an app and interact with them the same way you would with a mouse and keyboard.

Which apps can I use this with?

It's built for Cursor and other AI apps that support the same connection standard, such as Claude Code; check your app's settings to confirm it's supported.

Do I need an account or a paid key to use it?

No — the basic screen-capture and clicking features work without signing up for anything; only the optional automated 'agent' mode needs you to connect an AI model like Claude, GPT, or Gemini.

How hard is it to set up?

You install it with one command and then add a short snippet to your AI app's settings; no coding or building from source is required.

Does this work on Windows or Linux?

No — it's built specifically for Mac computers running a fairly recent version of macOS; separate community projects exist for Windows and Linux.

Will it need special permission from my Mac?

Yes — macOS will ask you to grant Screen Recording permission for screenshots, and Accessibility permission if you want it to click and type for you.

Can it tell me what's shown on my screen?

Yes — it can look at what's currently displayed and answer questions about it using a connected AI model, so you could ask what an error message says or what's inside a window.