timescale/pg-aiguide

MCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.

What it solves

AI coding assistants often generate PostgreSQL code that is outdated, lacks necessary constraints and indexes, or ignores modern features and real-world best practices. pg-aiguide provides AI agents with version-aware documentation and curated best practices to ensure they produce robust, performant, and maintainable database schemas and queries.

How it works

It functions as a set of "skills" and a Model Context Protocol (MCP) server. It provides AI agents with two primary capabilities:

  1. Semantic Search: A unified search tool (search_docs) that uses vector similarity and keyword search to query the official PostgreSQL manual, TimescaleDB, and PostGIS documentation.
  2. Curated Skills: A library of opinionated best practices (view_skill) covering schema design, indexing, data types, and performance tuning that agents can apply automatically.

Who it’s for

Developers using AI coding tools (such as Claude Code, Cursor, VS Code, or Gemini CLI) who want their AI assistants to write high-quality, modern PostgreSQL code.

Highlights

  • Version-Aware Documentation: Access to official PostgreSQL manuals scoped by version.
  • Coded Best Practices: Curated skills for indexing strategies, data integrity, and naming conventions.
  • Broad Agent Compatibility: Works with 40+ agents via npx skills or MCP server integration.
  • Extension Support: Includes documentation and skills for TimescaleDB and PostGIS, with pgvector coming soon.

Related

  • Project
    crystaldba/postgres-mcp

    An MCP server that enables AI agents to perform professional database administration, including index tuning, health checks, and query optimization for PostgreSQL.

  • Project
    tylergraydev/claude-code-tool-manager

    A desktop application that provides a visual interface to manage MCP servers, commands, and agents across multiple AI coding assistants like Claude Code and Cursor.

  • Project
    johnhuang316/code-index-mcp

    An MCP server that provides intelligent code indexing and AST-based analysis to help AI assistants navigate and understand complex codebases.

  • Project
    postmanlabs/postman-mcp-server

    An MCP server that connects AI agents and coding assistants to Postman workspaces, collections, and specifications to automate API testing and client code generation.

  • Project
    arabold/docs-mcp-server

    Grounded Docs MCP Server is a local, version‑aware documentation indexer that scrapes official docs (web, GitHub, npm, PyPI, local files), converts them to searchable text, and optionally adds vector embeddings. It exposes a simple MCP (SSE) API so AI coding assistants (Claude, Cline, Copilot, Gemini‑CLI, etc.) can retrieve exact documentation passages, reducing hallucinations while keeping data private.