Skip to content

Pgmcp

An MCP server to query any Postgres database in natural language.

Install

$brew install pgmcp

Install command taken from the project's README or registry entry. Always review code before running it.

PGMCP - PostgreSQL Model Context Protocol Server

PGMCP connects AI assistants to any PostgreSQL database through natural language queries. Ask questions in plain English and get structured SQL results with automatic streaming and robust error handling.

Works with: Cursor, Claude Desktop, VS Code extensions, and any MCP-compatible client

Quick Start

PGMCP connects to your existing PostgreSQL database and makes it accessible to AI assistants through natural language queries.

Prerequisites

  • PostgreSQL database (existing database with your schema)
  • OpenAI API key (optional, for AI-powered SQL generation)

Basic Usage

# Set up environment variables
export DATABASE_URL="postgres://user:password@localhost:5432/your-existing-db"
export OPENAI_API_KEY="your-api-key"  # Optional

# Run server (using pre-compiled binary)
./pgmcp-server

# Test with client in another terminal
./pgmcp-client -ask "What tables do I have?" -format table
./pgmcp-client -ask "Who is the customer that has placed the most orders?" -format table
./pgmcp-client -search "john" -format table

Here is how it works:

👤 User / AI Assistant
         │
         │ "Who are the top customers?"
         ▼
┌─────────────────────────────────────────────────────────────┐
│                    Any MCP Client                           │
│                                                             │
│  PGMCP CLI  │  Cursor  │  Claude Desktop  │  VS Code  │ ... │
│  JSON/CSV   │  Chat    │  AI Assistant    │  Editor   │     │
└─────────────────────────────────────────────────────────────┘
         │
         │ Streamable HTTP / MCP Protocol
         ▼
┌─────────────────────────────────────────────────────────────┐
│                    PGMCP Server                             │
│                                                             │
│  🔒 Security    🧠 AI Engine      🌊 Streaming              │
│  • Input Valid  • Schema Cache    • Auto-Pagination         │
│  • Audit Log    • OpenAI API      • Memory Management       │
│  • SQL Guard    • Error Recovery  • Connection Pool         │
└─────────────────────────────────────────────────────────────┘
         │
         │ Read-Only SQL Queries
         ▼
┌─────────────────────────────────────────────────────────────┐
│                Your PostgreSQL Database                     │
│                                                             │
│  Any Schema: E-commerce, Analytics, CRM, etc.               │
│  Tables • Views • Indexes • Functions                       │
└─────────────────────────────────────────────────────────────┘

External AI Services:
OpenAI API • Anthropic • Local LLMs (Ollama, etc.)

Key Benefits:
✅ Works with ANY PostgreSQL database (no assumptions about schema)
✅ No schema modifications required  
✅ Read-only access (100% safe)
✅ Automatic streaming for large results
✅ Intelligent query understanding (singular vs plural)
✅ Robust error handling (graceful AI failure recovery)
✅ PostgreSQL case sensitivity support (mixed-case tables)
✅ Production-ready security and performance
✅ Universal database compatibility
✅ Multiple output formats (table, JSON, CSV)
✅ Free-text search across all columns
✅ Authentication support
✅ Comprehensive testing suite

Features

Similar plugs

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…

Explore related