vision-primitives-mcpImage & Video ProcessingAI & Machine LearningAutonomous AgentszouyuanqingAlicenseBqualityDmaintenanceMCP server providing 26 visual tools for text-only LLMs, enabling description, coordinate location, OCR, annotation, cropping/zooming, anomaly scanning, and computer control with switchable VLM backends. Updated 3 months ago (2026-08-05 11:16 UTC)279MIT