Agentโ™ฅ๏ธŽAge
Catalog

Ui.Vision MCP

Official

by A9T9 ยท TypeScript

MCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input

io.github.A9T9/uivision-mcp MCP Server

This MCP server provides tools for browser and desktop automation. It supports OCR and image recognition, and can perform real mouse and keyboard input, enabling automated interaction with user interfaces. The project is associated with browser automation and testing workflows, with topics spanning web scraping and data-driven tests.

๐Ÿ› ๏ธ Key Features

  • OCR
  • Image recognition
  • Real mouse and keyboard input

๐Ÿš€ Use Cases

  • Browser and desktop automation
  • Web scraping
  • Data-driven tests
  • Browser extension and browser automation workflows

โšก Developer Benefits

  • Automates UI interaction using real mouse and keyboard events
  • Combines OCR/image recognition with automation for assisted recognition-driven flows

โš ๏ธ Limitations

  • Not enough server details provided to describe supported platforms, tool interfaces, or constraints

Topics

ai-agentsbrowser-automationbrowser-extensioncomputer-usedesktop-automationimage-recognitionmacro-recordermcpmcp-serverocrselenium-ideweb-automationbrowser-automation-ai-api