timescale/pg-aiguide

Registry

Summary

pg-aiguide is an MCP server and Claude Skill designed to enhance AI coding tools' ability to generate high-quality PostgreSQL code by providing specialized Postgres skills and documentation access.

Key features

• MCP server for PostgreSQL integration
• Claude Skill for AI-assisted coding
• Access to Postgres documentation and skills
• Designed to improve AI-generated SQL code
• Python-based implementation

Use cases

• Enhancing AI coding assistants for PostgreSQL development
• Providing real-time Postgres documentation to AI tools
• Improving accuracy of AI-generated database queries
• Integrating Postgres expertise into Claude workflows
• Supporting developers using AI for SQL code generation

README excerpt

# pg-aiguide **AI-optimized PostgreSQL expertise for coding assistants** pg-aiguide helps AI coding tools write dramatically better PostgreSQL code. It provides: - **Semantic search** across the official PostgreSQL manual (version-aware) - **AI-optimized “skills”** — curated, opinionated Postgres best practices used automatically by AI agents - **Extension ecosystem docs**, starting with TimescaleDB, with more coming soon Use it as: - **Agent Skills** via `npx skills` — works with Claude Code, Cursor, Codex, Gemini CLI, and 40+ other agents - a **public MCP server** that can be used with any AI coding agent, or - a **Claude Code plugin** optimized for use with Claude's native skill support. ## ⭐ Why pg-aiguide? AI coding tools often generate Postgres code that is: - outdated - missing constraints and indexes - unaware of modern PG features - inconsistent with real-world best practices pg-aiguide fixes that by giving AI agents deep, versioned PostgreSQL knowledge and proven patterns. ### See the difference https://github.com/user-attachments/assets/5a426381-09b5-4635-9050-f55422253a3d <details> <summary>Video Transcript </summary> Prompt given to Claude Code: > Please describe the schema you would create for an e-commerce website two times, first with the tiger mcp server disabled, then with the tiger mcp server enabled. For each time, write the schema to its own file in the current working directory. Then compare the two files and let me know which approach generated the better schema, using both qualitative and quantitative reasons. For this example, only use standard Postgres. Result (summarized): - **4× more constraints** - **55% more indexes** (including partial/expression indexes) - **PG17-recommended patterns** - **Modern features** (`GENERATED ALW

Topics