Unified Neo4j GraphRAG server combining vector similarity search, fulltext search, and search-augmented Cypher queries into a single implementation. Solves the critical limitation where LLMs cannot directly use Neo4j search indexes in Cypher by generating embeddings server-side and injecting them as parameters. Includes production-ready safeguards with automatic data sanitization for large embeddings and text content, intelligent token-aware response truncation limiting outputs to 8,000 tokens, and property size warnings to optimize query performance.
Cognium trust score
85%
Tier
Verified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-28.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.