A Model Context Protocol server for image optimization with advanced transformations powered by Sharp, enabling resize, convert, batch process, crop, watermark, and favicon generation from URLs or local files.
Enables MCP clients to analyze, inspect, and manipulate images and videos with deterministic FFmpeg/sharp tools and pluggable AI providers, returning timestamped, evidence-backed results that can be independently re-verified.
Bridges local vision engines (Tesseract.js OCR and Sharp preprocessing) with Ollama vision models for image analysis, comparison, text localization, and browser screenshot annotation over MCP-compliant HTTP/SSE transports.