pgEdge Postgres MCP Server and Natural Language Agent

The pgEdge Natural Language Agent enables access to the pgEdge Postgres Model Context Protocol (MCP) Server, allowing you to use natural language queries when interacting with a Postgres database.

Pre-Release

This software is in pre-release status. Test thoroughly before production use.

Not for Public-Facing Applications

This MCP server provides LLMs with read access to your entire database schema and data. It should only be used for internal tools, developer workflows, or environments where all users are trusted. For public-facing applications, consider using the pgEdge RAG Server instead. Read the full comparison →

MCP Server Features

Natural Language to SQL - Ask questions in plain English
Read-Only Protection - All queries execute in read-only transactions
Multiple LLM Support - Anthropic Claude, OpenAI, or Ollama (local/free)
Web Interface - Modern React-based chat UI
CLI Client - Production chat client with Anthropic prompt caching
Secure - TLS, token/user authentication, read-only enforcement

How the MCP server works:

flowchart LR
    A[User Question] --> B[LLM]
    B --> C[SQL Query]
    C --> D[MCP Server]
    D --> E[PostgreSQL]
    E --> F[Results]
    F --> B
    B --> G[Answer]

Schema extraction - The server loads table/column metadata from PostgreSQL.
Query generation - The LLM converts natural language to SQL.
Safe execution - Queries run in read-only transactions.
Result formatting - Answers are returned to the user.

User Guide

For server operators and end users:

Choosing the Right Solution - MCP Server vs RAG Server
Configuration - All configuration options
Authentication - Users, tokens, and access control
CLI Client - Command-line interface
Security - Security best practices
Troubleshooting - Common issues and solutions

Reference Pages:

Tools - Database query, schema, search tools
Resources - System info and schema resources
Prompts - Guided workflow prompts
Examples - Query examples

For Developers building applications that use the MCP server:

Overview - Integration approaches
MCP Protocol - Protocol details
API Reference - HTTP endpoints
Building Chat Clients - Client development

Advanced Topics:

Custom Prompts & Resources - Extend functionality
Knowledgebase - Documentation search system
LLM Proxy - Server-side LLM integration

For project contributors:

Development Setup - Local development
Architecture - System design
Testing - Test suites
CI/CD - Automation pipelines

License

This project is licensed under the PostgreSQL License.