Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

Clawd Cursor

clawdcursor.com

  • Free plan
  • Windows
  • macOS
  • Linux
  • Self-hosted
7.2 Club score Visit clawdcursor.com

What Clawd Cursor is

Clawd Cursor gives AI agents local control of desktop applications for GUI tasks where a native API or command-line option is unavailable. It maps screen elements using accessibility information and OCR, assigning stable IDs and confidence scores; screenshots are used when needed. Agents can click and type, and actions can be checked against an expected result. The maker describes the tool as local, localhost-only by default, and without telemetry, with every tool call passing through one safety layer. It can connect through stdio MCP or an HTTP MCP daemon, and the listed MCP hosts include Claude Code, Cursor, Windsurf, OpenClaw, and Zed. Clawd Cursor provides seven recommended compound tools and 98 granular tools for compatibility and debugging; its maker says it works with any model. It supports Windows, macOS 12 or later, and Linux X11 or Wayland. The software is free and MIT licensed. Installation requires Node.js 20 or later. Desktop control requires one-time consent; macOS also requires Accessibility permission, while Screen Recording is optional for vision fallback.

Who it suits

Clawd Cursor suits developers connecting AI agents to desktop interfaces when a native API or CLI is not available. It is intended for local GUI tasks and requires consent for desktop control.

Good to know, and what to watch

  • Maps screen elements using accessibility data and OCR
  • Actions can be checked against expected outcomes
  • Local and localhost-only by default
  • Supports Windows, macOS, and Linux
  • Works with listed MCP hosts and any model, according to its maker
  • Installation requires Node.js 20 or later
  • Desktop control requires one-time consent
  • macOS requires Accessibility permission

Clawd Cursor

Free

Free plan

The verdict

Clawd Cursor provides local desktop control with screen mapping and action checks for agent-driven GUI work. Check the Node.js requirement and platform permissions before setting it up.

What the maker publishes

Connection modes
Agents can connect through stdio MCP or an HTTP MCP daemon on 127.0.0.1:3847/mcp. source
Installation requirement
The GitHub README says Node.js 20 or later is required. source
Integrations
The site lists Claude Code, Cursor, Windsurf, OpenClaw, and Zed as MCP hosts. source
Intended use
The README describes it as a last-mile option for GUI tasks where a native API or CLI is unavailable. source
License
The site identifies Clawd Cursor as MIT licensed. source
Local operation
The maker describes it as local, localhost-only by default, and without telemetry. source
Model support
The maker says it works with any model; the daemon can also use a configured built-in LLM. source
Operating systems
It supports Windows x64/ARM64, macOS 12 or later, and Linux X11/Wayland. source
Permissions
Desktop control requires one-time consent; macOS also requires Accessibility permission, while Screen Recording is optional for vision fallback. source
Safety
Every tool call passes through one safety layer, and actions can be checked against an expected outcome. source
Screen reading
It combines accessibility data and OCR into a confidence-scored map with stable element IDs, using screenshots only when needed. source
Tools
It offers 7 recommended compound tools and 98 granular tools for compatibility and debugging. source
What it does
Clawd Cursor gives AI agents local control of desktop apps through a screen map, actions such as clicks and typing, and action verification. source

Checked against the maker's pages on 29 Sept 2026.