Skip to content
ai-supply.store
ExplorarCategoríasClasificacionesComunidadAgent APIFAQ
Iniciar sesiónRegístrate gratis
catalog / Data & ETL / ClickHouse MCP Server
◇MCP serverData & ETLFree

ClickHouse MCP Server

Official ClickHouse MCP server — run read-safe SQL and explore databases and tables.

@ai-supply
Instalaciones2.2k
↗ Repositorio fuente
← More Data & ETLData & ETL leaderboard →How we grade security →Source ↗

ClickHouse MCP Server

mcp-clickhouse is an official Model Context Protocol server that connects ClickHouse, the high-performance OLAP database, to AI assistants.

It exposes tools including run_query to execute SQL (read-only by default, with writes gated behind an explicit flag), list_databases to enumerate databases, and list_tables to browse tables with pagination. This lets an agent explore schemas and run analytical queries against a ClickHouse cluster safely.

It is aimed at analysts and engineers who want natural-language, read-safe access to ClickHouse analytics data.

Rating rank
#1
of 24 in Data & ETL
Install rank
#22
of 24 in Data & ETL
Security score
100/100 · A
safe
Security rank
#1
of 24 in Data & ETL
Installs
2.2k
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: Safe · 100100/100 · grade Ascanned 2h ago

Only compromise signals — malicious or tampered code (leaked secrets, backdoors, path traversal, a dropped executable) — reduce the score. Dangerous-by-capability traits (shell, network, injection strings, pickle) are shown as risk surface: expected for some capabilities — a security tool ships offensive code on purpose — so they do not sink the grade.

Compromise signals
None — no malicious or tampered code detected in the scanned source.
What this capability can do · med confidence (static)
⚑ filesystem⚑ network⚑ secrets
Risk surface (9)
External endpoints declaredlowexpected for this capabilityClickHouse-mcp-clickhouse-ccef141/.github/workflows/publish.yml
1 distinct host(s)
External endpoints declaredlowexpected for this capabilityClickHouse-mcp-clickhouse-ccef141/.gitignore
3 distinct host(s)
Suspicious network referencesmediumClickHouse-mcp-clickhouse-ccef141/README.md
raw IP URL (17 URLs)
Egress to a private/loopback hosthighexpected for this capabilityClickHouse-mcp-clickhouse-ccef141/README.md
127.0.0.1
External endpoints declaredmediumexpected for this capabilityClickHouse-mcp-clickhouse-ccef141/README.md
11 distinct host(s)
Broad capability surfacelowClickHouse-mcp-clickhouse-ccef141/mcp_clickhouse/chdb_prompt.py
3 high-impact capability categories referenced — verify least-privilege
Suspicious code patternsmediumClickHouse-mcp-clickhouse-ccef141/tests/test_context_config_override.py
dynamic os import
Embedded credentialshighexpected for this capabilityClickHouse-mcp-clickhouse-ccef141/tests/test_pagination.py
found: hardcoded credential
Vulnerable dependenciescritical
39 known vulnerabilities in: authlib@1.6.10, cryptography@46.0.7, diskcache@5.6.3, fastmcp@2.14.7, idna@3.11, pydantic-settings@2.13.1, pyjwt@2.12.1, python-multipart@0.0.26
✔ verified source · pinned ClickHouse-mcp-clickhouse-ccef141
Check against a policy

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

OWASP AI control mapping
7passed
7flagged
1runtime-enforced
5governance

Evaluated against the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any control to see the findings.

OWASP Top 10 for LLM Applications
✓LLM01Prompt InjectionPassed
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: hardcoded credential (CWE-798)
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Vulnerable dependencies — 39 known vulnerabilities in: authlib@1.6.10, cryptography@46.0.7, diskcache@5.6.3, fastmcp@2.14.7, idna@3.11, pydantic-settings@2.13.1, pyjwt@2.12.1, python-multipart@0.0.26 (CWE-1395)
✓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.
⚠LLM05Improper Output Handlingmedium
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — dynamic os import
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s)
•External endpoints declared — 3 distinct host(s)
•Egress to a private/loopback host — 127.0.0.1 (CWE-918)
•External endpoints declared — 11 distinct host(s)
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege (CWE-272)
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: hardcoded credential (CWE-798)
✓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.
§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.
OWASP Machine Learning Security Top 10
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
§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.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Vulnerable dependencies — 39 known vulnerabilities in: authlib@1.6.10, cryptography@46.0.7, diskcache@5.6.3, fastmcp@2.14.7, idna@3.11, pydantic-settings@2.13.1, pyjwt@2.12.1, python-multipart@0.0.26 (CWE-1395)
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
⚠ML09Output Integritymedium
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — dynamic os import
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.

Consume ClickHouse MCP Server 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/clickhouse-mcp-server

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

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

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

# MCP tool
install_listing({ "slug": "clickhouse-mcp-server" })
OpenAPI spec →
vlatest
✓ Security: Safe · 1002h 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

Capacidades de IA gratuitas y verificadas en seguridad: skills, MCPs, plugins, agents, datasets y mucho más, cada una con su puntuación y control de actualidad, pensadas por igual para personas y agents.

api · v3.1status · all green
Contacto
support@ai-supply.storesecurity@ai-supply.store
Catálogo
  • Explorar
  • Categorías
  • Clasificaciones
  • Benchmarks
  • Seguridad
Comunidad
  • Comunidad
  • FAQ
Para agentes
  • Inicio rápido (60s)
  • Autorizar un agente
  • Agent API
  • Especificación OpenAPI
Para desarrolladores
  • Publicar
  • Panel
Cuenta
  • Crear cuenta
  • Iniciar sesión
  • Configuración
Legal
  • Términos
  • Acuerdo de editor
  • Uso aceptable
  • Privacidad