macOS automation MCP server with screen capture, UI interaction, and AI analysis
If you already use Peekaboo, the peekaboo mcp server is the piece that lets your assistant work with it directly. macOS automation MCP server with screen capture, UI interaction, and AI analysis.
Peekaboo brings high-fidelity screen capture, AI analysis, and complete GUI automation to macOS. Version 3 adds native agent flows and multi-screen automation across the CLI and MCP server.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Pixel — accurate captures (windows, screens, menu bar) with optional Retina 2x scalingNatural — language agent that chains Peekaboo tools (see, click, type, scroll, hotkey, menu, window, app, dock, space)Action — first UI automation for routine clicks/scrolls, with background process-targeted input by default when a target is knownMulti — provider AI through Tachikoma, including hosted, local, and OpenAI-/Anthropic-compatible providersArchitecture — docs/ARCHITECTURE.mdPermissions — docs/permissions.mdRequirements — see docs/platform-support.md. Node 22+ is only needed for the npm MCP wrapper and pnpm helper scriptsBecause this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.
Configuration is passed through the environment: PEEKABOO_AI_PROVIDERS, TEXT_FIELD_ID, BUTTON_ID. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Peekaboo's toolset — Pixel, Natural, Action and 4 more — is a fair guide to whether it matches your workflow. It is maintained by steipete; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| Pixel | accurate captures (windows, screens, menu bar) with optional Retina 2x scaling. |
| Natural | language agent that chains Peekaboo tools (see, click, type, scroll, hotkey, menu, window, app, dock, space). |
| Action | first UI automation for routine clicks/scrolls, with background process-targeted input by default when a target is known. |
| Multi | provider AI through Tachikoma, including hosted, local, and OpenAI-/Anthropic-compatible providers. |
| Architecture | [docs/ARCHITECTURE.md](docs/ARCHITECTURE.md) |
| Permissions | [docs/permissions.md](docs/permissions.md) |
| Requirements | see [docs/platform-support.md](docs/platform-support.md). Node 22+ is only needed for the npm MCP wrapper and pnpm helper scripts. |
{
"mcpServers": {
"peekaboo": {
"command": "npx",
"args": ["-y", "@steipete/peekaboo"],
"env": {
"PEEKABOO_AI_PROVIDERS": "your-value",
"TEXT_FIELD_ID": "your-value",
"BUTTON_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| PEEKABOO_AI_PROVIDERS | Configuration value read at startup. | Optional |
| TEXT_FIELD_ID | Configuration value read at startup. | Optional |
| BUTTON_ID | Configuration value read at startup. | Optional |
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.
Thousands of open models on tap — run image, video and audio generation through Replicate's hosted API.