genpark-harris-corner-feature-detector-skill

Harris corner and salient feature detector using spatial gradient autocorrelation matrix analysis.

Part of the GenPark AI Agent Skills Matrix. Production-ready, zero external dependencies, native Python 3.9+ standard library.

Architecture

flowchart TD
    A[Image Input Matrix] --> B[Spatial Processing Kernel]
    B --> C[Feature & Geometry Extraction]
    C --> D[Structured Output / Segments]
    D --> E[MCP Protocol Endpoint]

Features

• Zero Third-Party Dependencies: Pure Python standard library (math, collections).
• Precision Computer Vision: Optimized spatial convolution and disjoint-set Union-Find.
• Native MCP Protocol Support: Integrated JSON-RPC 2.0 stdio server ready for Claude Desktop, Cursor, and Windsurf.

Installation

pip install genpark-harris-corner-feature-detector-skill

Or clone directly:

git clone https://github.com/alphaparkinc/genpark-harris-corner-feature-detector-skill.git
cd genpark-harris-corner-feature-detector-skill
python example_usage.py

Quick Start

from client import *
# Refer to example_usage.py for end-to-end execution

Model Context Protocol (MCP) Setup

Add to your claude_desktop_config.json or cursor.json:

{
  "mcpServers": {
    "genpark-harris-corner-feature-detector-skill": {
      "command": "python",
      "args": ["-m", "genpark-harris-corner-feature-detector-skill.mcp_server"]
    }
  }
}

License

MIT License. Copyright (c) 2026 AlphaPark Inc. & Alpha-Park.