Postgres Scout MCP

Scout your PostgreSQL databases with AI - A production-ready Model Context Protocol server with built-in safety features, monitoring, and data quality tools.

What You Get

You ask:

"How healthy is my production database? Any urgent issues?"

Postgres Scout returns:

Overall Health Score: 78/100

Component Breakdown

Issues Found

• HIGH — Table orders has 34% bloat (2.1 GB wasted). VACUUM FULL recommended.
• MEDIUM — 3 unused indexes on sessions consuming 890 MB.
• LOW — Cache hit ratio for analytics_events is 71% (target: >90%).

Recommendations

• Run VACUUM FULL orders during maintenance window
• Drop unused indexes: idx_sessions_legacy, idx_sessions_old_token, idx_sessions_temp
• Consider adding analytics_events to shared_buffers or partitioning by date

That's getHealthScore — one of 38 tools covering exploration, diagnostics, optimization, monitoring, data quality, and safe writes.

Quick Start

Claude Code

claude mcp add postgres-scout -- npx -y postgres-scout-mcp postgresql://localhost:5432/mydb

Then ask: "Show me the largest tables and whether they have any bloat issues."

{
  "mcpServers": {
    "postgres-scout": {
      "command": "npx",
      "args": ["-y", "postgres-scout-mcp", "postgresql://localhost:5432/mydb"],
      "type": "stdio"
    }
  }
}

{
  "postgres-scout": {
    "command": "npx",
    "args": ["-y", "postgres-scout-mcp", "postgresql://localhost:5432/mydb"]
  }
}

{
  "mcpServers": {
    "postgres-scout-readonly": {
      "command": "npx",
      "args": ["-y", "postgres-scout-mcp", "--read-only", "postgresql://localhost:5432/production"],
      "type": "stdio"
    },
    "postgres-scout-readwrite": {
      "command": "npx",
      "args": ["-y", "postgres-scout-mcp", "--read-write", "postgresql://localhost:5432/development"],
      "type": "stdio"
    }
  }
}

Tools

Explore — understand your database

• listDatabases — databases the user has access to
• getDatabaseStats — size, cache hit ratio, connection info
• listSchemas — all schemas in the current database
• listTables — tables with size and row statistics
• describeTable — columns, constraints, indexes, and more

Query — run and analyze

• executeQuery — run SELECT queries (or writes in read-write mode)
• explainQuery — EXPLAIN plans for performance analysis
• optimizeQuery — optimization recommendations for a specific query

Diagnose — find problems before they find you

• getHealthScore — overall health score with component breakdown
• detectAnomalies — anomalies in performance, connections, and data
• analyzeTableBloat — bloat analysis for VACUUM planning
• getSlowQueries — slow query analysis (requires pg_stat_statements)
• suggestVacuum — VACUUM recommendations based on dead tuples and bloat

Optimize — make it faster

• suggestIndexes — missing index recommendations from query patterns
• `sug

... View full README on GitHub