RPA

Level AMCP ecosystemNot an MCP ServerLocal

Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and image recognition.

Overview

Ui.Vision is a browser and desktop automation tool with an MCP server that lets AI assistants create, edit, and run reusable macros. Users can build automations via the macro recorder, the uiv.* JavaScript API, or an AI assistant to fill forms, extract web data, and test websites. OCR and image recognition help locate on-screen text and controls, and desktop apps and remote desktop interfaces can be automated too. Scripts, logs, and screenshots are available after each run.

⭐ 2.1kBrowser AutomationTypeScriptRepo ↗Updated 2026-11-04

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "uivision-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "uivision-mcp-bridge"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/A9T9/RPA

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "uivision-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "uivision-mcp-bridge"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers