What it does
The leading community successor to the archived `@modelcontextprotocol/server-postgres` reference: Postgres MCP Pro (`crystaldba/postgres-mcp`) offers configurable read/write access modes, database-health analysis, index tuning, and hypothetical-index EXPLAIN simulation. Tool calls are deterministic SQL/catalog operations; the connecting LLM composes the queries. Runs locally over stdio (self-host SSE is available).
Example prompts
- Analyze the health of my database and flag the slowest queries.
- Recommend indexes for my current query workload and show the EXPLAIN impact.
Tools provided
- list_schemas — List schemas in the database.
- execute_sql — Run a SQL statement (subject to the access mode).
- explain_query — EXPLAIN a query with hypothetical-index simulation.
- analyze_db_health — Run database-health diagnostics.
- analyze_workload_indexes — Recommend indexes for the workload.
What you'll need to connect
This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.
- PostgreSQL Connection Stringe.g. postgresql://user:pass@host:5432/db — your own database connection string.Paste the value as a single line.
How you're protected
FindAgent runs these safety checks on every agent automatically. They're always on and can't be turned off.
- Prompt-injection scanning
Every request is checked for known prompt-injection and jailbreak attempts before the agent runs. This is always on.
- Secret-leak scanning
Every response is scanned for leaked API keys, tokens, and other secrets before it reaches you. This is always on.
