Skip to content
ai-supply.store
ExplorarCategoriasClassificaçõesComunidadeAgent APIFAQ
EntrarCadastre-se grátis
catalog / Data & ETL / Neo4j MCP Servers
◇MCP serverData & ETLFree

Neo4j MCP Servers

Neo4j Labs MCP servers for Cypher queries, knowledge-graph memory, and Aura instance management.

@ai-supply
Instalações9.7k
↗ Repositório fonte
← More Data & ETLData & ETL leaderboard →How we grade security →Source ↗

Neo4j MCP Servers

mcp-neo4j is a collection of Model Context Protocol servers from Neo4j Labs that let AI assistants work with Neo4j graph databases and Aura using natural language.

The repo includes several servers: mcp-neo4j-cypher inspects a database schema and runs generated read/write Cypher queries; mcp-neo4j-memory stores and retrieves entities and relationships as a personal knowledge graph; and mcp-neo4j-cloud-aura-api manages Neo4j Aura cloud instances (create, scale, find, enable features).

It targets developers and data teams who want their agent to query graph data and manage Neo4j infrastructure conversationally.

Rating rank
#1
of 24 in Data & ETL
Install rank
#21
of 24 in Data & ETL
Security score
33/100 · D
review
Security rank
#15
of 24 in Data & ETL
Installs
9.7k
cat avg 164k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Data & ETL leaderboard →
! Security: Review · 3333/100 · grade Dscanned 18h ago
⚠ 1 compromise signal20 risk-surface · 9/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → api.github.com, astral.sh, docs.github.com, pypi.org, registry.npmjs.org, yourdomain.com,https, neo4j.com, modelcontextprotocol.io +20

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not.

OWASP Top 10 for LLM Applications
⚠LLM02Sensitive Information Disclosurecompromise · high
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: hardcoded credential · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/Dockerfile (CWE-798)compromise
⚠LLM07System Prompt Leakagecompromise · high
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: hardcoded credential · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/Dockerfile (CWE-798)compromise
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Vulnerable dependencies — 363 known vulnerabilities in: aiohttp@3.12.13, authlib@1.6.0, cryptography@45.0.5, fastmcp@2.10.2, h11@0.14.0, idna@3.10, mcp@1.10.1, pygments@2.19.2 (CWE-1395)known CVE · -25 pts
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/README.md (CWE-77)risk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Path traversal sequences — '../' present in content or name · neo4j-contrib-mcp-neo4j-dbc01ba/.github/workflows/github-registry-aura-manager.yml (CWE-22)risk surface
•Suspicious code patterns — pipe-to-shell install · neo4j-contrib-mcp-neo4j-dbc01ba/.github/workflows/pr-mcp-neo4j-cloud-aura-api.yml (CWE-494)risk surface
•Suspicious code patterns — dynamic code execution · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/tests/integration/test_http_transport_IT.py (CWE-95)risk surface
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/.editorconfigexpected
•External endpoints declared — 2 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/.github/workflows/github-registry-aura-manager.ymlexpected
•External endpoints declared — 4 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/.github/workflows/publish-aura-manager.ymlexpected
•External endpoints declared — 5 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/README.mdexpected
•Egress to a private/loopback host — 127.0.0.1 · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/tests/integration/conftest.py (CWE-918)expected
•External endpoints declared — 3 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/tests/integration/conftest.pyexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/tests/integration/test_http_transport_IT.py (CWE-272)risk surface
•External endpoints declared — 9 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/tests/unit/test_utils.pyexpected
•External endpoints declared — 7 distinct host(s) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/README.mdexpected
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
◷LLM10Unbounded ConsumptionRuntime-enforced
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Vulnerable dependencies — 363 known vulnerabilities in: aiohttp@3.12.13, authlib@1.6.0, cryptography@45.0.5, fastmcp@2.10.2, h11@0.14.0, idna@3.10, mcp@1.10.1, pygments@2.19.2 (CWE-1395)known CVE · -25 pts
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/README.md (CWE-77)risk surface
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Path traversal sequences — '../' present in content or name · neo4j-contrib-mcp-neo4j-dbc01ba/.github/workflows/github-registry-aura-manager.yml (CWE-22)risk surface
•Suspicious code patterns — pipe-to-shell install · neo4j-contrib-mcp-neo4j-dbc01ba/.github/workflows/pr-mcp-neo4j-cloud-aura-api.yml (CWE-494)risk surface
•Suspicious code patterns — dynamic code execution · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/tests/integration/test_http_transport_IT.py (CWE-95)risk surface
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (15) · hygiene / uncategorized
•Unrecognized file type — '.editorconfig' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/.editorconfigrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/.gitignorerisk surface
•Unrecognized file type — '.prettierignore' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/.prettierignorerisk surface
•Unrecognized file type — '.prettierrc' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/.prettierrcrisk surface
•Unrecognized file type — '.dockerignore' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/.dockerignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/Dockerfilerisk surface
•Suspicious network references — raw IP URL (4 URLs) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/tests/integration/conftest.pyrisk surface
•Suspicious network references — raw IP URL (22 URLs) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cloud-aura-api/tests/integration/test_http_transport_IT.pyrisk surface
•Unrecognized file type — '.flake8' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/.flake8risk surface
•Unrecognized file type — '.python-version' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/.python-versionrisk surface
•Suspicious network references — raw IP URL (34 URLs) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/tests/integration/test_http_transport_IT.pyrisk surface
•Suspicious network references — raw IP URL (1 URLs) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-cypher/tests/integration/test_sse_transport_IT.pyrisk surface
•Suspicious network references — raw IP URL (19 URLs) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-data-modeling/tests/integration/test_http_transport_IT.pyrisk surface
•Unrecognized file type — '.ttl' is not on the allowlist · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-data-modeling/tests/resources/blueplaques.ttlrisk surface
•Suspicious network references — raw IP URL (31 URLs) · neo4j-contrib-mcp-neo4j-dbc01ba/servers/mcp-neo4j-memory/tests/integration/test_http_transport_IT.pyrisk surface
✔ verified source · pinned neo4j-contrib-mcp-neo4j-dbc01ba · changed since last scan (-25 pts)
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/neo4j-mcp-server/check). Click a policy:

Consume Neo4j MCP Servers programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/neo4j-mcp-server

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/neo4j-mcp-server/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add neo4j-mcp-server

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/neo4j-mcp-server/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "neo4j-mcp-server" })
OpenAPI spec →
vlatest
! Security: Review · 331d ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Recursos de IA gratuitos e com segurança verificada — skills, MCPs, plugins, agents, datasets e muito mais, cada um com nota e acompanhamento de atualização, feitos tanto para pessoas quanto para agents.

api · v3.1status · all green
Contato
support@ai-supply.storesecurity@ai-supply.store
Catálogo
  • Explorar
  • Categorias
  • Classificações
  • Benchmarks
  • Segurança
Comunidade
  • Comunidade
  • FAQ
Para agentes
  • Início rápido (60s)
  • Autorizar um agente
  • Agent API
  • Especificação OpenAPI
Para desenvolvedores
  • Publicar
  • Painel
Conta
  • Criar conta
  • Entrar
  • Configurações
Legal
  • Termos
  • Acordo de editor
  • Uso aceitável
  • Privacidade