Postgres Ai Guide

Created By
timescale6 months ago
Overview

What is pg-aiguide?

pg-aiguide is an AI-optimized tool designed to enhance PostgreSQL coding by providing AI coding assistants with better knowledge and practices for writing PostgreSQL code.

How to use pg-aiguide?

You can use pg-aiguide as a public MCP server with any AI coding agent or as a Claude Code plugin. Installation instructions are provided for various environments including VS Code, Visual Studio, and more.

Key features of pg-aiguide?

  • Semantic search across the official PostgreSQL manual, tailored for specific versions.
  • AI-optimized skills that incorporate best practices for PostgreSQL.
  • Documentation for the TimescaleDB extension and more to come.

Use cases of pg-aiguide?

  1. Assisting AI coding tools in generating accurate PostgreSQL schemas.
  2. Providing best practices for schema design and indexing strategies.
  3. Enhancing the quality of PostgreSQL code generated by AI agents.

FAQ from pg-aiguide?

  • Can pg-aiguide be used with any AI coding agent?

Yes! It can be utilized as a public MCP server or as a plugin for Claude Code.

  • What types of best practices does pg-aiguide provide?

It offers guidance on schema design, indexing strategies, data integrity, and modern PostgreSQL features.

  • Is pg-aiguide free to use?

Yes! pg-aiguide is available for free.

Server Config

{
  "mcpServers": {
    "pg-aiguide": {
      "url": "https://mcp.tigerdata.com/docs"
    }
  }
}
Project Info
Created At
6 months ago
Updated At
6 months ago
Author Name
timescale
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago