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.
How to install screenhand?
manushi4/screenhand
$claude plugin marketplace add manushi4/screenhandInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install screenhand by running `claude plugin marketplace add manushi4/screenhand`, then use it for the current task and follow its documentation at https://github.com/manushi4/screenhand.
Related
6 picksType
- agent-browserBrowser automation for AI agentsJul 2026
- browser-harnessDirect browser control via CDP. Drives the user's real Chrome (or a Browser Use cloud browser) with coordinate clicks, screenshots, and Python helpers — no selector hunting. Requires the one-time `browser-harness` CLI install (see the skill's references/install.md).Jul 2026
- web-accessComplete web browsing and automation skill for Claude Code - intelligent tool selection, CDP browser automation, and site experience accumulationMay 2026
- dev-browserMarketplace for the dev-browser skillJul 2026
- webwrightTurn your coding agent into a SOTA browser agent. Drives a local Playwright workspace via one bash command at a time, saving screenshots and an action log into final_runs/run_<id>/, and visually self-verifies the result.Jun 2026
- ego-liteBrowser automation for AI agentsJul 2026
