Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Scores AI image/video generation prompts (0-100) against 18 models (Veo 3, Sora, Kling, Runway, Seedance, Midjourney, Flux, and more) before you spend a generation credit, then rewrites weak ones. Free, hosted remote MCP + npm/PyPI packages.
A MCP server that allows one to examine image metadata like EXIF, XMP, JFIF and GPS. This provides foundation for LLM-powered search and analysis of photo librares and image collections.
Quality signal
49/100 (Fair)
53/100 (Fair)
Install path
npx · high
npx · high
Engagement
3 0 0 8
2 0 0 39
Tools
Scores prompts on a 0-100 scale against 18 AI modelsScores creatives by visual similarity to proven winnersProvides enhancement briefs based on real market dataUses a corpus of 3,800+ long-running ads from 8 verticalsSupports npm and PyPI packages for integrationHosted free remote MCP server with live dashboard
Offline operation with no network dependenciesSupports multiple metadata segments: EXIF, GPS, XMP, ICC, IPTC, JFIF, IHDRAccepts image input via file paths, URLs, base64 strings, or buffersCompatible with JPEG, TIFF, HEIC/AVIF, and PNG image formatsProvides specialized tools for orientation, rotation, GPS extraction, and thumbnailsStandardized error handling for unsupported formats and network issues
