Screen Control runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 18 Sep 2026.
Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.
Today is the operative word: we check Screen Control every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Desktop UI automation for AI agents: screenshots, windows, mouse, keyboard, UI Automation, OCR
MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
Vision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
Screen observation, OCR and permission-controlled app input over MCP for Apple silicon Macs.
Web extraction, OCR (Japanese-strong), invoice and company data for AI agents. x402, no API key.
Secure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard
Real-time screen capture + AI vision for Claude — see, analyze, and OCR your screen
Answers built from our own checks of this server.