pg-aiguide MCP — Anwendungsfälle, Installieren & Live-Demo

Name: pg-aiguide MCP Server
Author: timescale

Warum nutzen

Hauptfunktionen

Unified search across PostgreSQL, TimescaleDB, PostGIS docs
Version-aware — results pinned to the PG version you ask about
Curated skills on schema design, indexing, modern PG features
Hosted MCP endpoint at https://mcp.tigerdata.com/docs
Also installable as a Claude plugin

Live-Demo

In der Praxis

pg-aiguide.replay ▶ bereit

0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "pg-aiguide": {
      "command": "uvx",
      "args": [
        "pg-aiguide"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "pg-aiguide": {
      "command": "uvx",
      "args": [
        "pg-aiguide"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "pg-aiguide": {
      "command": "uvx",
      "args": [
        "pg-aiguide"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "pg-aiguide": {
      "command": "uvx",
      "args": [
        "pg-aiguide"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "pg-aiguide",
      "command": "uvx",
      "args": [
        "pg-aiguide"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "pg-aiguide": {
      "command": {
        "path": "uvx",
        "args": [
          "pg-aiguide"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add pg-aiguide -- uvx pg-aiguide

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: pg-aiguide

How to get an agent to write a production-grade Postgres schema

👤 Backend engineers starting a new service ⏱ ~20 min intermediate

Wann einsetzen: You want generated SQL that actually survives a code review.

Voraussetzungen

Add the pg-aiguide MCP — Point client at https://mcp.tigerdata.com/docs or install the Claude plugin

Ablauf

State the domain

I need a schema for a multi-tenant SaaS with orgs, users, projects, invites. Before writing SQL, consult pg-aiguide for schema design and identifier best practices.✓ Kopiert

→ Agent cites view_skill output
Review constraints + indexes

Show me every constraint you added and why. Any redundant indexes?✓ Kopiert

→ Per-index justification
Check modern features

Use search_docs to verify you're using GENERATED ALWAYS AS IDENTITY (not SERIAL), and NULLS NOT DISTINCT where appropriate.✓ Kopiert

→ Modern idioms applied

Ergebnis: Schema with sensible constraints, right identity columns, and indexes you can defend.

Fallstricke

Agent overuses indexes — write-heavy tables slow down — Ask for workload-aware indexing — tell it the expected reads/writes ratio

Kombinieren mit: postgres

How to get expert context when reading an EXPLAIN plan

👤 Devs optimizing a slow query ⏱ ~15 min intermediate

Wann einsetzen: You have EXPLAIN ANALYZE output and don't know what's normal.

Ablauf

Share the plan

[paste EXPLAIN ANALYZE] — use pg-aiguide to identify what each node does and typical reasons for cost here.✓ Kopiert

→ Node-by-node diagnosis citing docs
Ask for index advice

Based on the plan, propose one index change. Verify the index type (BTREE vs BRIN vs partial) via pg-aiguide.✓ Kopiert

→ Concrete CREATE INDEX with justification

Ergebnis: Plan understood, change defended with docs.

Kombinieren mit: postgres

How to pick the right TimescaleDB hypertable settings

👤 Teams doing time-series on Postgres ⏱ ~15 min advanced

Wann einsetzen: First hypertable in a new service — many knobs.

Ablauf

State ingest shape

I'll ingest ~10k rows/sec of IoT sensor data, queries are last-24h and last-30d aggregates. Consult pg-aiguide for TimescaleDB hypertable chunk interval recommendations.✓ Kopiert

→ Chunk interval + compression policy rationale
Draft the table

Draft the CREATE TABLE + create_hypertable + compression policy.✓ Kopiert

→ Full DDL

Ergebnis: Hypertable config tuned for your ingest rate.

Kombinieren mit: postgres

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

pg-aiguide + postgres

Consult pg-aiguide for best practices, then actually apply them via postgres MCP

Use pg-aiguide to pick the right index for orders.user_id, then apply it via postgres MCP on the dev DB. Show EXPLAIN ANALYZE before/after.✓ Kopiert

pg-aiguide + github

Code-review a schema migration with docs-backed reasoning

Review PR #4421 which adds a new table. Use pg-aiguide to flag any choices that diverge from idiomatic PG 16.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
search_docs	query: str, product?: 'postgres'\|'timescale'\|'postgis', version?: str	Look up a specific feature, function, or setting	free
view_skill	skill: 'schema-design'\|'indexing'\|'data-types'\|'performance'	Apply best-practice guidance before writing schema	free

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Hosted endpoint — reasonable-use rate limits
Tokens pro Aufruf: 300-1500 tokens per search result
Kosten in €: Free
Tipp: Use view_skill for broad guidance, search_docs only when you need a specific citation.

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: None — docs only

Credential-Speicherung: None

Datenabfluss: Your queries go to mcp.tigerdata.com

Niemals gewähren: Nothing to grant; no DB access

This MCP doesn't execute SQL — pair with postgres MCP when you need to run queries.

Fehlerbehebung

Häufige Fehler und Lösungen

search_docs returns outdated info

Pin version: search_docs(query, version='17') for PG 17 specifics.

Connection to mcp.tigerdata.com fails

Check corporate firewall; fall back to the Claude plugin (local) install.

Prüfen: curl -I https://mcp.tigerdata.com/docs

view_skill returns generic output

Specify the skill slug exactly — unknown slugs fall back to generic summaries.

Alternativen

pg-aiguide vs. andere

Alternative	Wann stattdessen	Kompromiss
postgres MCP	You need to execute SQL, not just read docs	No curated best-practice layer
Supabase MCP	Supabase-specific project management	Supabase-locked

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen