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.
Search the Archive of Our Own (AO3) and delegate full-fic reading to a secondary model (Gemini), so the agent recommends from the actual text, not the author's blurb. pip install ao3-mcp
AI image generation & editing MCP server with 1,500+ curated prompt library, smart prompt enhancement, and multi-provider routing (local ComfyUI, MeiGen Cloud, OpenAI-compatible APIs).
Quality signal
41/100 (Fair)
56/100 (Good)
Install path
pip · high
npx · high
Engagement
1 0 0 1
1 0 0 1,669
Tools
Search AO3 with fandom, ship, character, rating, word count, completion, and sorting filtersFuzzy input resolution to canonical AO3 tags and namesRead 1–20 full fanfics per call using Gemini model for detailed structured reportsCache downloaded fics locally for 24 hours to reduce repeated AO3 requestsThrottle requests to AO3 respecting politeness and Cloudflare restrictionsSupports configurable Gemini API key and model selection
Supports 11 leading image and video generation modelsIncludes 1,446 curated prompt templatesMulti-provider backend support: local ComfyUI, MeiGen Cloud, OpenAI-compatible APIsParallel sub-agent orchestration for batch generationStandalone CLI mode for scripting and CI integration
