omniparser-autogui-mcp
Analyzes screen content using OmniParser and automates GUI operations via Model Context Protocol, supporting customizable window targeting and remote processing for enhanced workflow automation on Windows.
Supercharge Your AI with omniparser-autogui-mcp
Unlock the full potential of omniparser-autogui-mcp through LangDB's AI Gateway. Get enterprise-grade security, analytics, and seamless integration with zero configuration.
Free tier available • No credit card required
Set to 1 if it does not work with other clients (such as LibreChat)
Address and port of the server if you want OmniParser processing to be done on another device (e.g. 127.0.0.1:8000)
Python IO encoding setting
utf-8Host for SSE communication instead of stdio
Port for SSE communication instead of stdio
Path to caption model for OmniParser configuration
Language setting for OCR
enBox threshold setting for OmniParser configuration
Path to SOM model for OmniParser configuration
Device setting for OmniParser configuration
Caption model name for OmniParser configuration
Security Notice
Your environment variables and credentials are securely stored and encrypted. LangDB never shares these configuration values with third parties.
Model Context Protocol server enabling Windows desktop automation with full AutoIt function integration, supporting mouse, keyboard, window, process, and system operations, plus file access, screenshots, and automation prompt templates via stdio or WebSocket transport.
Added May 30, 2025
Provides Model Context Protocol tools for fetching, processing, summarizing, and extracting structured web content using Cloudflare Browser Rendering, supporting enhanced LLM context and documentation search capabilities.
5 toolsAdded May 29, 2025
Provides Model Context Protocol (MCP) capabilities for computer control including mouse and keyboard automation, screen capture with OCR, window management, and drag-and-drop operations using PyAutoGUI, RapidOCR, and ONNXRuntime without external dependencies.
Added May 29, 2025
Automates standardized documentation generation from GitHub and Google Drive sources using templates, supports multiple file types, tracks document history, and integrates AI-enhanced content via Perplexity within the Model Context Protocol framework.
3 toolsAdded May 30, 2025
Automates the PlayCanvas Editor using an LLM via Model Context Protocol, offering comprehensive tools for managing entities, assets, scenes, and store content with enhanced integration through Claude or Cursor clients.
Added May 30, 2025