Trust Card · Static snapshot

ClickHouse__mcp-clickhouse C

69/100 · 2 findings (1 critical) · scope broad · Ranked #31 of 53 scanned.

Scanned 2026-09-09 · engine v0.1.0 (8 regex rules, OWASP-mapped) · upstream ClickHouse/mcp-clickhouse @ 0b1afe6 (2026-09-08)

Score breakdown

security 60

permissions 60

provenance 75

reliability 85

stability 85

Score constrained by 1 critical and 1 high-severity findings.

Fix first (2 critical/high)

Severity	Rule	Finding	Remediation
CRITICAL	`AT-SEC-002` (LLM02)	Hardcoded Credential or API Secret `tests/test_auth_config.py:858` Evidence: `secret = "constructor-secret-value"`	Move credentials to secure environment variables or a key vault. Never commit API keys.
HIGH	`AT-SEC-005` (ASI02)	Unrestricted Recursive File Deletion / Modification `tests/test_chdb_tool.py:56` Evidence: `self.addCleanup(lambda: os.path.exists(temp_path) and os.unlink(temp_path))`	Enforce strict jail/root directories and require explicit human-in-the-loop confirmation before file deletions.

Permissions

Scope: broad · Shell: disabled · Network egress: yes · File deletion: enabled · Human approval: none

Provenance

License: Apache-2.0 · Lockfile: no · Security policy: no · Signals: unverified origin

Independently scanned by the AgentTrust registry (not self-reported by the project). Static analysis only — no code executed, findings need human triage, counts may include test/example code. Static snapshot; re-scan before relying on it: npx @eulogik/agenttrust scan https://github.com/ClickHouse/mcp-clickhouse. Scores move with every upstream commit; pages refresh weekly. How scoring works.