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 ALWAYS AS IDENTITY, NULLS NOT DISTINCT)
Cleaner naming & documentation
Conclusion:
Key features
01. missing constraints and indexes
02. unaware of modern PG features
03. inconsistent with real-world best practices
pg-aiguide produces more robust, performant, maintainable schemas.
🚀 Quickstart
Agent Skills
Install curated PostgreSQL best-practice skills for your AI coding agent:
Works with Claude Code, Cursor, Codex, Gemini CLI, VS Code, and 40+ other agents.
For even deeper PostgreSQL knowledge, also add the MCP server to give your agent semantic search over the official PostgreSQL, TimescaleDB, and PostGIS manuals.
MCP Server
For semantic search over PostgreSQL, TimescaleDB, and PostGIS documentation, add the public MCP server:
claude plugin marketplace add timescale/pg-aiguide
claude plugin install pg@aiguide
Install by environment
This repo serves as a claude code marketplace plugin. To install, run:
claude plugin marketplace add timescale/pg-aiguide
claude plugin install pg@aiguide
This plugin uses the skills available in the skills directory as well as our
publicly available MCP server endpoint hosted by TigerData for searching PostgreSQL documentation.
Run the following to add the MCP server to Gemini CLI:
gemini mcp add -s user pg-aiguide "https://mcp.tigerdata.com/docs" -t http
Add the following to your global OpenCode config file (~/.config/opencode/opencode.json), or to a
project level opencode.json. See the OpenCode config docs for
more about file locations, and the MCP server docs for more
about the mcp options.
Once installed, pg-aiguide can answer Postgres questions or design schemas.
Simple schema example prompt
Create a Postgres table schema for storing usernames and unique email addresses.
Complex schema example prompt
You are a senior software engineer. You are given a task to generate a Postgres schema for an IoT device company.
The devices collect environmental data on a factory floor. The data includes temperature, humidity, pressure, as
the main data points as well as other measurements that vary from device to device. Each device has a unique id
and a human-readable name. We want to record the time the data was collected as well. Analysis for recent data
includes finding outliers and anomalies based on measurements, as well as analyzing the data of particular devices for ad-hoc analysis. Historical data analysis includes analyzing the history of data for one device or getting statistics for all devices over long periods of time.
Features
Documentation Search (MCP Tools)
search_docs
Unified search tool supporting semantic (vector similarity) and keyword (BM25) search across multiple documentation sources:
postgres - Official PostgreSQL manual, scoped by version
tiger - Tiger Data's documentation (TimescaleDB and ecosystem)
postgis - PostGIS spatial extension documentation
Skills (AI-Optimized Best Practices)
view_skill
Exposes curated, opinionated PostgreSQL best-practice skills used automatically by AI coding assistants.
These skills provide guidance on:
Exploring existing PostgreSQL schemas and objects
Schema design
Indexing strategies
Data types
Data integrity and constraints
Naming conventions
Performance tuning
Modern PostgreSQL features
🔌 Ecosystem Documentation
Supported today:
TimescaleDB (docs + skills)
PostGIS (docs)
Coming soon:
pgvector
We welcome contributions for additional extensions and tools.
