scanned 1mo ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓
Postgres MCP Pro
Postgres MCP Pro is a Model Context Protocol server that gives AI agents deep, guarded access to PostgreSQL. It goes beyond plain query execution: agents can inspect schemas, run configurable read-only or read/write SQL, diagnose slow queries, and get principled index recommendations backed by the query planner.
Key features
Configurable access modes: unrestricted for local development, restricted read-only for production safety
Index tuning that simulates hypothetical indexes and reports the estimated plan-cost change
Database health checks covering bloat, cache hit rates, vacuum status, and connection saturation
EXPLAIN/EXPLAIN ANALYZE plan inspection so agents can reason about and optimize queries
Works with any Postgres 13+ instance over a standard connection string, local or managed
Ships as a container and via pip/uvx for drop-in wiring into MCP clients
It is a practical bridge for coding agents that need to understand a real database's structure and performance rather than blindly issuing SQL.
Curated mirror of the open-source Postgres MCP Pro (MIT). Get it from the source.
! Security: Review · 7575/100 · grade Bscanned 1mo ago
✓ no compromise signals11 risk-surface · 7/20 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)
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.