Best for
- Developers using AI coding tools (Claude Code, Cursor, Codex, Gemini CLI).
- Those wanting to ensure generated PostgreSQL code is modern, reliable, and performant.
P
pg-aiguide
Community
AI-optimized PostgreSQL expertise for coding assistants
GitHub source repository ↗
50FMRS · D
pg-aiguide significantly improves the quality of PostgreSQL code generated by AI coding tools by providing semantic search and best-practice skills. It is suitable for developers needing high-quality database code, but requires network access and relies on external services.
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), and extension ecosystem docs (starting with TimescaleDB). It can be used as Agent Skills, a public MCP server, or a Claude Code plugin.
Tools
search_docs
Unified search tool supporting semantic (vector similarity) and keyword (BM25) search across multiple documentation sources, including PostgreSQL, TimescaleDB, and PostGIS.
view_skill
Exposes curated, opinionated PostgreSQL best-practice skills covering schema design, indexing strategies, data types, data integrity, naming conventions, performance tuning, and modern features.
Setup
Install as Agent Skills: run npx skills add timescale/pg-aiguide --skill postgres. As an MCP server, add https://mcp.tigerdata.com/docs to your client config (e.g., mcpServers JSON). As a Claude Code plugin: run claude plugin marketplace add timescale/pg-aiguide and claude plugin install pg@aiguide.
claude_desktop_config.json
{
"mcpServers": {
"pg-aiguide": {
"url": "https://mcp.tigerdata.com/docs"
}
}
}
Fit and risk
Not for
- Applications requiring direct database connections or query execution.
- Environments needing local, offline operation.
Required permissions
- As a remote HTTP server, it receives queries and returns documentation.
- As skills, it may be invoked automatically by AI agents.
Risks and side effects
- Public server may contain outdated or inaccurate information from docs.
- Remote server exposed to network risks.
- AI agents may generate plausible but unvalidated code.
Troubleshooting
- Ensure network connectivity to `mcp.tigerdata.com`.
- Check the URL in your client's MCP config is correct.
- For skills, verify `npx skills` is installed and version compatible.
- For Claude Code plugin, ensure you have a supported Claude version.
Use cases
Provide deep PostgreSQL knowledge to AI coding agents for better schema generation.
Search PostgreSQL-related documentation across multiple sources.
Automate best practice application via skills.
Supported clients
Claude CodeFull support
CursorFull support
VS CodeFull support
CodexFull support
Gemini CLIFull support
WindsurfFull support