Clawdcursor MCP server

Clawd Cursor

Safe desktop control for any AI agent. Compiles the screen into a UI map and acts on elements by stable id (screenshot/vision only as a last resort), verifies its own actions, and gates everything through one safety checkpoint. Local · cross-OS · any model.

Quickstart · Why it's different · The engine · How it works · Tools · Platforms · Changelog

<!-- ─────────────────────────────────────────────────────────────────────────── DEMO: the single highest-leverage thing on this page for a visual tool. Record a 15–25s screen capture of clawdcursor driving a real app end-to-end (open app → find a field by name → type → verify), export to docs/demo.gif, and uncomment the block below (it will sit right under the hero).

Opening an app, finding a field by name, typing, and verifying the result — accessibility-first, locally. ─────────────────────────────────────────────────────────────────────────── -->

What it is

Clawd Cursor is a local MCP server that gives any tool-calling agent &mdash; Claude Code, Cursor, Windsurf, OpenClaw, the Claude Agent SDK, or your own loop &mdash; safe control of the real desktop. It clicks, types, reads the screen, opens apps, and drives any GUI the way a human would: native apps, the browser, even a canvas.

Most "let an agent use the computer" tools take a screenshot and feed it to a vision model &mdash; slow, expensive, and brittle. Clawd Cursor compiles the screen into one UI map: it fuses the accessibility tree and OCR into a confidence-scored set of elements, each tagged with a stable elNN id, and acts on elements by id &mdash; not pixel coordinates. Coordinates appear only in the last-resort screenshot/vision tier (live pixels off the current frame), for canvas-only apps or tasks that genuinely need spatial reasoning. The result is cheaper, faster, private, and &mdash; uniquely &mdash; it checks that each action actually did what it claimed**.

If a human can do it on a screen, your agent can too. No API, no integration, no problem &mdash; only the right sequence of reads, clicks, keys, and waits. Use it as the last-mile fallback: native API exists? Use it. CLI? Use it. Clawd Cursor is for the click, the legacy app, the GUI with no public surface.

Why it's different

Shortened. The full README is on GitHub.