@rameshv29
Basic information
PostgreSQL performance analysis and optimization MCP server
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"postgreSQL-analyzer-mcp": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}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
PostgreSQL Analyzer MCP is a Model Context Protocol (MCP) server for PostgreSQL database performance analysis and optimization. It leverages 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 Streamable HTTP transport, allowing centralized deployment and access by any MCP-compatible client (e.g., Amazon Q Developer CLI, Claude).
Install locally (Python 3.12+, pip) or via Docker. Start the server with python src/main.py or by running the Docker container. Point your MCP client to http://your-server:8000/mcp using Streamable HTTP transport. Database credentials can be provided via AWS Secrets Manager (recommended) or directly when calling tools.
Yes, it operates in read-only mode by default. All database connections use `SET TRANSACTION READ ONLY` to prevent accidental modifications, and query execution is limited to SELECT, EXPLAIN, and SHOW commands.
Python 3.12+ (or Docker), a PostgreSQL database (Amazon Aurora or RDS supported), and optionally an AWS account with Secrets Manager credentials.
You can store credentials in AWS Secrets Manager (recommended) and pass the secret name when calling tools, or provide host, port, dbname, username, and password directly in tool arguments.
Yes, use Docker to build and run the container on any remote server. For secure access, consider setting up a reverse proxy with SSL/TLS and authentication middleware.
Enable `pg_stat_statements` and `pg_buffercache` extensions, and set `shared_preload_libraries = 'pg_stat_statements'` with `pg_stat_statements.track = all` in postgresql.conf.
A MCP (model context protocol) server that gives the LLM access to and knowledge about relational databases like SQLite, Postgresql, MySQL & MariaDB, Oracle, and MS-SQL.
Model Context Protocol Servers
The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.
A Model Context Protocol server that provides read-only access to MySQL databases. This server enables LLMs to inspect database schemas and execute read-only queries.
Comments