manushi4/Screenhand

Give AI eyes and hands on your desktop. Open-source MCP server for desktop automation — screenshots, UI control, browser automation, OCR. Works with Claude, Cursor, and any MCP client. macOS + Windows.

45
/ 100
Emerging

This tool gives AI agents the ability to control your desktop applications and web browsers, just like a human. It takes your high-level instructions, like "search for X on Instagram," and translates them into precise clicks, typing, and form filling across different apps without needing constant screenshots or slow AI interpretations. It's designed for anyone who uses AI assistants (like Claude or Cursor) and wants them to automate tasks across their computer.

Available on npm.

Use this if you want your AI assistant to perform complex, multi-step workflows across various desktop applications and websites efficiently and reliably.

Not ideal if you primarily use AI for text-based tasks or do not need your AI assistant to interact directly with your computer's user interface.

desktop-automation workflow-automation AI-assistants browser-automation digital-operations
Maintenance 10 / 25
Adoption 6 / 25
Maturity 20 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

TypeScript

License

AGPL-3.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/manushi4/Screenhand"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.