Set-of-Marks (SoM) bounding box resolution and relative viewport coordinate mapper for computer-use vision agents
genpark-gui-screen-som-coordinate-mapper-skill
Production-Grade Vision Agent & Computer-Use Skill • 100% Standard Library Python • Native Model Context Protocol (MCP)
🌐 GenPark MCP Hub Showcase • 📦 Official Website • 📖 Documentation
genpark-gui-screen-som-coordinate-mapper-skill is a deterministic, zero-dependency Python skill engineered with 100% production-grade functional parity for autonomous vision agents, computer-use GUI automation, and multimodal spatial grounding.
Executive Capability: Set-of-Marks (SoM) bounding box resolution and relative viewport coordinate mapper for computer-use vision agents
⚡ Key Highlights & Value 🐍 Zero External pip Dependencies: Runs instantly on standard Python 3.9+ with zero environment bloat. 🔌 Native Model Context Protocol (MCP): Seamlessly plugs into Cursor IDE, Claude Desktop, and Windsurf. 🎯 100% Production-Grade Dynamic Execution: Real mathematical scoring, spatial geometry mapping, and deterministic outputs without static placeholders. 🚀 Low Latency & High Reliability: Sub-millisecond execution overhead tailored for high-framerate visual agent loops.
Connect this skill to Claude Desktop, Cursor, or any MCP-compliant client:
Parameter Type Required Description ------:---:--- querypayload string / dict Yes Primary input parameter parsed and executed deterministically outputformat json / dict Yes Standardized response schema containing execution telemetry
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/alphaparkinc--genpark-gui-screen-som-coordinate-mapper-skill.html)
Geometric spatial relationship grounding evaluator verifying relative positional assertions between objects and UI controls
Alpha-Park/genpark-gui-screen-som-coordinate-mapper-skillSet-of-Marks (SoM) bounding box resolution and relative viewport coordinate mapper for computer-use vision agents
Alpha-Park/genpark-agent-action-trajectory-video-summarizer-skillMulti-frame GUI computer-use action trajectory summarizer detecting dead clicks and UI rendering latency stalls
Alpha-Park/genpark-browser-dom-accessibility-tree-pruner-skillBrowser DOM accessibility tree pruner filtering non-interactive noise and generating dense actionable trees for web agents
alphaparkinc/genpark-multimodal-visual-hallucination-verifier-skillMultimodal visual hallucination verifier cross-checking vision model claims against ground-truth OCR and bounding box metadata
alphaparkinc/genpark-agent-action-trajectory-video-summarizer-skillMulti-frame GUI computer-use action trajectory summarizer detecting dead clicks and UI rendering latency stalls
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.