"Home Assistant Community Store" matching MCP connectors:

The world's first named AI prompt quality score. Score, optimize, and compare LLM prompts before they hit any model. Free tier available. Built on PEEM, RAGAS, G-Eval, and MT-Bench frameworks. x402-native on Base.

Korean crypto × AI media MCP — channel stance, daily briefs, RAG, canonical store, AI personas.

Vector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.

Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.

Search your knowledge bases from any AI assistant using hybrid RAG.

ContextBook is an open-source MCP server that gives AI tools a persistent, searchable context library. Store information as Books and Pages, retrieve exactly what's needed via natural-language semantic search - injected on demand, not pre-loaded. Works with Cursor, Claude, Windsurf, and any MCP-compatible client. Self-hostable, MIT licensed.

Causal graph memory engine for AI agents. Scores memories using relevance × connectivity × reactivation, connects them in a causal graph, and actively forgets irrelevant ones. 11 MCP tools including store, recall, search, traverse, and explain.

Persistent memory for AI agents. Search, store, and recall across sessions.

Semantic memory for AI agents. Store, recall, and forget memories with entity extraction and fact-based retrieval. Self-hostable, privacy-first, works with any LLM.

Memory system for AI agents with semantic search. Store and recall memories with ease.