Skip to content
ai-supply.store
खोजेंश्रेणियाँलीडरबोर्डसमुदायAgent APIFAQ
साइन इनमुफ़्त साइन अप
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
इंस्टॉल2.2k
⟳ upstream v0.4.1 · updated 1mo ago
↗ सोर्स रिपॉज़िटरी
← More Data & ETLData & ETL leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals8capabilities surfaced1known CVE9of 20 OWASP controls clear
Suspicious network referencesBroad capability surfaceSuspicious code patternsVulnerable dependencies
scanned 1mo ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

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
75/100 · B
review
Security rank
#10
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: Review · 7575/100 · grade Bscanned 1mo ago
✓ no compromise signals9 risk-surface · 5/20 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⚑ network⚑ secrets
egress → pypi.org, img.shields.io, glama.ai, gofastmcp.com, sql.clickhouse.com, docs.astral.sh, i.ytimg.com, www.youtube.com +2

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, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Vulnerable dependencies — 12 known vulnerabilities in: click@8.3.2, diskcache@5.6.3, fastmcp@2.14.7, mcp@1.27.0 (CWE-1395)known CVE · -25 pts
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 2 distinct host(s) · ClickHouse-mcp-clickhouse-66f0d1b/.github/workflows/publish-mcp.ymlexpected
•External endpoints declared — 1 distinct host(s) · ClickHouse-mcp-clickhouse-66f0d1b/.github/workflows/publish.ymlexpected
•External endpoints declared — 3 distinct host(s) · ClickHouse-mcp-clickhouse-66f0d1b/.gitignoreexpected
•Egress to a private/loopback host — 127.0.0.1 · ClickHouse-mcp-clickhouse-66f0d1b/README.md (CWE-918)expected
•External endpoints declared — 11 distinct host(s) · ClickHouse-mcp-clickhouse-66f0d1b/README.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · ClickHouse-mcp-clickhouse-66f0d1b/mcp_clickhouse/chdb_prompt.py (CWE-272)risk surface
⚠LLM05Improper Output Handlingmedium
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — dynamic os import · ClickHouse-mcp-clickhouse-66f0d1b/tests/test_context_config_override.pyrisk surface
§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.
✓LLM01Prompt InjectionPassed
✓LLM02Sensitive Information DisclosurePassed
✓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.
✓LLM07System Prompt LeakagePassed
✓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 — 12 known vulnerabilities in: click@8.3.2, diskcache@5.6.3, fastmcp@2.14.7, mcp@1.27.0 (CWE-1395)known CVE · -25 pts
⚠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 · ClickHouse-mcp-clickhouse-66f0d1b/tests/test_context_config_override.pyrisk 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.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓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 (6) · hygiene / uncategorized
•Unrecognized file type — '.dockerignore' is not on the allowlist · ClickHouse-mcp-clickhouse-66f0d1b/.dockerignorerisk surface
•Unrecognized file type — '.editorconfig' is not on the allowlist · ClickHouse-mcp-clickhouse-66f0d1b/.editorconfigrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · ClickHouse-mcp-clickhouse-66f0d1b/.gitignorerisk surface
•Unrecognized file type — '.python-version' is not on the allowlist · ClickHouse-mcp-clickhouse-66f0d1b/.python-versionrisk surface
•Unrecognized file type — '.?' is not on the allowlist · ClickHouse-mcp-clickhouse-66f0d1b/Dockerfilerisk surface
•Suspicious network references — raw IP URL (17 URLs) · ClickHouse-mcp-clickhouse-66f0d1b/README.mdrisk surface
✔ verified source · pinned ClickHouse-mcp-clickhouse-66f0d1b · changed since last scan · +egress static.modelcontextprotocol.io, clickhouse.com
Check against a policy

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

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: Review · 751mo 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

मुफ़्त, सुरक्षा-जाँची गई AI क्षमताएँ — skills, MCPs, plugins, agents, datasets और बहुत कुछ, हर एक ग्रेडेड और ताज़गी-ट्रैक्ड, और इंसानों तथा agents दोनों के लिए बनाई गई।

api · v3.1status · all green
संपर्क करें
support@ai-supply.storesecurity@ai-supply.store
कैटलॉग
  • खोजें
  • श्रेणियाँ
  • लीडरबोर्ड
  • बेंचमार्क
  • सुरक्षा
  • Scan a repo
समुदाय
  • समुदाय
  • FAQ
एजेंट के लिए
  • क्विकस्टार्ट (60s)
  • एजेंट अधिकृत करें
  • Agent API
  • OpenAPI स्पेसिफिकेशन
बिल्डर्स के लिए
  • प्रकाशित करें
  • डैशबोर्ड
खाता
  • खाता बनाएँ
  • साइन इन
  • सेटिंग्स
कानूनी
  • नियम व शर्तें
  • प्रकाशक अनुबंध
  • स्वीकार्य उपयोग नीति
  • गोपनीयता