# Waldo

> Waldo is the pair of hands any AI agent can borrow. He sees every window, presses every button and types into every field on your Mac, and asks you first before money, messages, passwords or deletes.

Waldo is a free, open source MCP server for macOS (Apache 2.0). Any AI agent that speaks MCP can use it: Claude Code, Codex, Gemini CLI, Cursor, and others. It reads the accessibility tree instead of screenshots, presses controls in background apps without moving your pointer, and checks that each act really happened. Four hard stops always ask the human first: money, sending as you, passwords and keys, and deleting things. Only a real mouse click can approve them. Pushing the pointer into the top-left corner of the screen stops every tool for every agent. Waldo was called OS Control before version 0.3.0.

## Start here

- [Waldo home](https://justusewaldo.com/): what Waldo is, how it works, the hard stops, and install
- [Install](https://justusewaldo.com/#install): build from source, then register with your agent
- [Source code on GitHub](https://github.com/justusewaldo/waldo): README, changelog, and security policy
- [Full text for language models](https://justusewaldo.com/llms-full.txt): every answer on this site

## Guides

- [How do I let Claude Code control my Mac?](https://justusewaldo.com/guides/claude-code-mac/): Give Claude Code hands on your Mac with Waldo, a free MCP server. Install, grant, register, then ask. Money, messages, and deletes still ask you first.
- [Is there an MCP server that lets an AI agent use my Mac?](https://justusewaldo.com/guides/mcp-server-macos/): Yes. Waldo is a free, open source MCP server for macOS. Any MCP agent can see windows, press buttons, and type, and he asks you before anything risky.
- [How do I give Codex, Gemini CLI, or Cursor hands on my Mac?](https://justusewaldo.com/guides/codex-gemini-cursor-mac/): Waldo is one MCP server for every agent. Point Codex, Gemini CLI, or Cursor at waldo mcp, grant two macOS permissions, and ask in plain words.
- [What is computer use for AI agents?](https://justusewaldo.com/guides/what-is-computer-use/): Computer use lets an AI agent work a computer's apps: look, click, and type. How it sees the screen, why it needs brakes, and where Waldo fits.
- [How do I stop an AI agent paying, sending, or deleting without me?](https://justusewaldo.com/guides/ai-agent-hard-stops/): Four hard stops in code make an AI agent ask you first before money, messages, passwords, or deletes. Only a click from your own mouse can say yes.
- [Should AI agents read screenshots or the accessibility tree?](https://justusewaldo.com/guides/accessibility-tree-vs-screenshots/): How AI agents see a Mac: screenshots and pixel coordinates, or the accessibility tree with names and roles. Speed, accuracy, and where each one fails.
- [How do I stop an AI agent at once on my Mac?](https://justusewaldo.com/guides/stop-ai-agent-mac/): Push the pointer into the top-left corner, run waldo stop, or press Stop everything. Every tool, for every agent, stops until you say go.

## Questions

- What is Waldo? Waldo is the pair of hands any AI can borrow. He is a free, open source MCP server for macOS. He sees every window, presses every button, and types into every field. When money, messages, passwords, or deletes come up, he stops and asks you.
- How do I let Claude Code use my Mac? Install Waldo and register him with Claude Code. Run git clone https://github.com/justusewaldo/waldo, then cd waldo, make install, waldo grant, and make register. Start a new Claude Code session and ask in plain words.
- Does Waldo work with Codex, Gemini CLI, Cursor, and other agents? Yes. Waldo speaks MCP, the open standard agents use to pick up tools. Codex, Gemini CLI, Cursor and friends all take the same command: waldo mcp.
- Is it safe to let an AI agent use my Mac? Waldo is wired so a person always holds the yes. Four hard stops live in his code, not in a prompt: money, sending as you, passwords and keys, and deleting things. Only a click from your own mouse can approve one.
- Can the AI approve its own actions? No. The ask panel takes no keys and refuses any click that did not come from your own mouse. Software clicks bounce off, and so do accessibility presses. Both are tested.
- How do I stop an AI agent at once? Push your pointer into the top-left corner of the screen. Every tool, for every agent, stops until you say go. Or run waldo stop.
- Does Waldo read the screen with screenshots? He reads the accessibility tree, the same one screen readers use. Every control arrives with its name, role, and real position, so any model picks the right thing instead of guessing at pixels. He takes a screenshot when the model asks to look.
- Does Waldo send my screen to the cloud? Waldo runs on your Mac and sends nothing to any server. What he reads goes to your agent, and your agent sends it to the model you chose, under that agent's own rules.
- What does Waldo cost, and what do I need? Waldo is free and open source under Apache 2.0. You need a Mac, Rust, and the Xcode command line tools, plus an agent that speaks MCP. He has run on Apple silicon with macOS 26.5 and 27.
- Was Waldo called OS Control? Yes. OS Control became Waldo in version 0.3.0. The tools, the gates, and the checks work as before. The command is now waldo.