NON906/omniparser-autogui-mcp
Local LLM Tools

NON906/omniparser-autogui-mcp

Get This Tool  →

Overview

NON906/omniparser-autogui-mcp integrates Microsoft’s Omniparser visual screen parser with local GUI automation scripts. It allows AI models to see screen elements and interact with them using mouse coordinates and keyboard events.

This is a major step toward autonomous GUI agents, enabling bots to automate repetitive browser clicks, desktop software inputs, and testing workflows.

✔ Pros

Visual coordinate extraction; Automates legacy desktop applications; Supports complex multi-app pipelines

✖ Cons

High security execution risks; Requires coordinate calibration

At a Glance

  • Pricing Free
  • Category Local LLM Tools
  • Added On June 9, 2026