Back to MCP Trust Indexm8ven
74
/ 100
1 month ago
glama

Neo4j Knowledge Graph MCP Server

Provides LLM clients with a persistent, scalable knowledge graph memory system that supports semantic retrieval, contextual recall, and temporal awareness.

→ henrychong-ai/mcp-neo4j-knowledge-graph· listed on glama
Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 4 credentials: EMBEDDING_API_KEY, NEO4J_PASSWORD, OPENAI_API_KEY, RERANK_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configCF_ACCOUNT_ID
configEMBEDDING_API_BASE_URL— =https://api.cloudflare.com/client/v4/accounts/<id>/ai/v1
configEMBEDDING_API_ENDPOINT
🔐 secretEMBEDDING_API_KEY— your-cf-workers-ai-token>
configEMBEDDING_BACKFILL_CRON— One server-side instance owns all embedding writes: WRITE_EMBEDDINGS_LOCALLY=true (the default) plus a tight backfill cron (='/1 ').
configEMBEDDING_DIMENSIONS— NEO4J_VECTOR_DIMENSIONS == the model's NATIVE output dimension
configEMBEDDING_MODEL— @cf/qwen/qwen3-embedding-0.6b # native 1024 dimensions
configEMBEDDING_RATE_LIMIT_INTERVAL
configEMBEDDING_RATE_LIMIT_TOKENS
configEMBEDDING_STALE_CLAIM_MS— 300000 # (v2.4.0+) Claims older than this age are auto-released back
configENABLE_PROMETHEUS_METRICS— true # Enable metrics collection and HTTP endpoint
configLOG_LEVEL— warn # Log level: debug, info, warn, error, silent (default: warn)
configMEMORY_STORAGE_TYPE
configMOCK_EMBEDDINGS— With NO provider configured (and unset) the server runs keyword-only
configNEO4J_DATABASE— "": "neo4j",
🔐 secretNEO4J_PASSWORD— your_password
configNEO4J_SIMILARITY_FUNCTION— "": "cosine",
configNEO4J_URI— bolt://<your-neo4j-host>:7687
configNEO4J_USERNAME— neo4j # NOTE: NEO4J_USERNAME — "NEO4J_USER" is silently ignored
configNEO4J_VECTOR_DIMENSIONS— EMBEDDING_DIMENSIONS == == the model's NATIVE output dimension
configNEO4J_VECTOR_INDEX— entity_embeddings
🔐 secretOPENAI_API_KEY— your-openai-api-key
configOPENAI_EMBEDDING_MODEL— text-embedding-3-small # 1536 dimensions (default)
configRERANK_ACCOUNT_ID— your-account-id>
🔐 secretRERANK_API_KEY— your-cf-workers-ai-token>
configRERANK_ENABLED— Disabled unless =true AND an endpoint + key resolve. Fail-open on any error
configRERANK_ENDPOINT— =https://api.cloudflare.com/client/v4/accounts/<id>/ai/run/@cf/baai/bge-reranker-base
configRERANK_MODEL— @cf/baai/bge-reranker-base
configRERANK_TOP_K— Reranker configured, default 10 5 () cross-encoder, best-first
configTEST_INTEGRATION
configVITEST
configWRITE_EMBEDDINGS_LOCALLY— One server-side instance owns all embedding writes: =true (the default) plus a tight backfill cron (EMBEDDING_BACKFILL_CRON='/1 ').
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 1 concrete improvement we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/henrychong-ai-mcp-neo4j-knowledge-graph-fpdth5)](https://m8ven.ai/mcp/henrychong-ai-mcp-neo4j-knowledge-graph-fpdth5)
commit: 4bdb5afdf662e1223821ef9d3fe46d379bbdabd1
code hash: 0420297b540ac40a07a4b85d4c567ffbb81417e71945461752e23649fdaa06b5
verified: 6/22/2026, 12:57:06 PM
view raw JSON →