# crystaldba/postgres-mcp

Postgres MCP Pro provides configurable read/write access and performance analysis for you and your AI agents.

Repository: https://github.com/crystaldba/postgres-mcp
Canonical: https://ross.abutalabs.com/products/postgres-mcp
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-17T05:06:35+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 40, longevity 37
- inputs: {"age_days": 527, "days_push": 16, "days_rel": 474, "gap_med": 7, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3226, forks 370 (observed 2026-08-28T04:07:49.954055+00:00)

## What it is
Postgres MCP Pro is an open-source Model Context Protocol (MCP) server that gives AI agents and developers safe, configurable read/write access to PostgreSQL databases. It goes beyond a simple connection wrapper with index tuning, EXPLAIN plan analysis, database health checks, and schema-aware SQL generation.

## Use cases
- let AI agents safely query and analyze my postgres database
- tune database indexes for my workload automatically
- analyze slow queries with explain plans and hypothetical indexes
- check postgres health like vacuum, replication lag, and connection usage
- give cursor or claude read-only access to a production database
- generate schema-aware SQL with an AI coding assistant
- fix slow ORM queries in an AI-generated app

## When to choose
- you use AI coding agents (Cursor, Claude, etc.) with a PostgreSQL database
- you need safe, configurable SQL execution including read-only mode for production
- you want automated index tuning and query plan analysis
- you need database health diagnostics alongside AI access

## When to avoid
- you use MySQL, SQLite, or another non-Postgres database
- you need a general-purpose MCP server unrelated to databases
- you want a GUI database client rather than an MCP server for agents

## Facets
- artifact type: service
- maturity: active
- function: mcp, database, monitoring, benchmarking, search-engine
- domain: databases, developer-tools, large-language-models, performance
- platform: python, self-hosted, cli
- tags: postgres, mcp-server, index-tuning, explain-plans, database-health, sql-execution, ai-agents, docker

## Member repositories
- crystaldba/postgres-mcp (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.954055+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:44:16.434956+00:00, confidence not recorded.
  - readme: https://github.com/crystaldba/postgres-mcp (fetched 2026-08-28T04:07:49.954055+00:00, sha 57179dc67b7c)
- Data as of 2026-08-30T08:39:29.467469+00:00.