Advertise
MCP.so
Sign In

PostgreSQL Performance MCP Server

@rameshv29

Repository

Basic information

Category

Databases

License

MIT license

Transports

stdio

Author

rameshv29

About PostgreSQL Performance MCP Server

PostgreSQL performance analysis and optimization MCP server

PostgreSQL Performance MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "postgres-performance-mcp": {
      "command": "python",
      "args": [
        "server.py",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ]
    }
  }
}

PostgreSQL Performance MCP Server tools

11

Analyze database schema and provide optimization recommendations

Identify slow-running queries in the database

Analyze a SQL query and provide optimization recommendations

Recommend indexes for a given SQL query

Suggest optimized rewrites for a SQL query

Generate a comprehensive health dashboard for the database

Interactive wizard to optimize a SQL query step by step

Analyze index usage patterns and identify unused or inefficient indexes

Execute a read-only SQL query and return the results

Show PostgreSQL configuration settings with optional filtering

Check if the server is running and responsive

Overview

What is PostgreSQL Performance MCP?

PostgreSQL Performance MCP is a Model Context Protocol (MCP) server for PostgreSQL database performance analysis and optimization. It uses AI to help database administrators and developers analyze database structure, query performance, index usage, and configuration, providing actionable recommendations. It runs as a remote MCP server using SSE transport and is designed for use with MCP-compatible clients like Amazon Q Developer CLI and Claude.

How to use PostgreSQL Performance MCP?

Install Python 3.12+, clone the repository, install dependencies, and configure database credentials (optionally via AWS Secrets Manager). Start the server with python server.py --host 0.0.0.0 --port 8000. Connect any MCP-compatible client using the server URL and SSE transport, then call the available tools (e.g., analyze_database_structure, get_slow_queries, recommend_indexes) with the required parameters.

Key features of PostgreSQL Performance MCP

  • Database structure analysis with optimization recommendations
  • Query performance analysis and bottleneck identification
  • Index recommendations based on query patterns
  • Slow query identification and analysis
  • Database health dashboard with comprehensive metrics
  • Read-only query execution for safe verification

Use cases of PostgreSQL Performance MCP

  • Analyze database schema to improve table design and indexing
  • Identify and optimize slow-running queries
  • Get index recommendations for specific SQL queries
  • Generate a database health dashboard for monitoring
  • Safely execute read-only analytical queries against live databases

Frequently asked questions

1

Is PostgreSQL Performance MCP read-only?

Yes, by default all database connections use `SET TRANSACTION READ ONLY` to prevent accidental modifications. Query execution is strictly limited to SELECT, EXPLAIN, and SHOW commands.

2

What are the prerequisites to use PostgreSQL Performance MCP?

Python 3.12+, an Amazon Aurora or RDS PostgreSQL database, and optionally an AWS account for Secrets Manager. Recommended PostgreSQL extensions are `pg_stat_statements` and `pg_buffercache`.

3

How are database credentials managed?

Credentials can be stored in AWS Secrets Manager (recommended) or provided directly when calling tools. The secret must contain host, port, dbname, username, and password.

4

What transport does PostgreSQL Performance MCP use?

It uses Server-Sent Events (SSE) transport, allowing it to be deployed centrally as a remote MCP server accessible by any MCP-compatible client.

5

Is PostgreSQL Performance MCP production-ready?

No, this project is experimental and provided "as is" without warranty. All recommendations should be carefully reviewed before use in production environments.

Comments

More Databases MCP servers

nuzur

nuzur is a model-first database platform for MySQL and PostgreSQL. The MCP server lets any AI assistant or agent (Claude, Cursor, Gemini, or anything else that speaks MCP) design your schema, query your data, generate mi

MotherDuck's DuckDB MCP Server

motherduckdb

Local MCP server for DuckDB and MotherDuck

498

mcp-server-qdrant: A Qdrant MCP server

qdrant

An official Qdrant Model Context Protocol (MCP) server implementation

637

golfdata.online - Verified Golf Clubs

golfdata.online

Verified golf club data for AI agents: holes, par, address, phone, booking links, facilities, visitor rules and green fees for golf clubs in Spain (Canary Islands and mainland), expanding across Europe. Every fact comes

ClickHouse MCP Server

ClickHouse

Connect ClickHouse to your AI assistants.

818
Advertise