db-mcp-server MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

Multi-DB in one server — switch without restarting
Per-connection auto-generated tools (e.g. query_prod, schema_analytics)
TimescaleDB-native tools for time-series ops
Oracle: 10g-23c, RAC, Cloud Wallet

Live-Demo

In der Praxis

db.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": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "db",
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "db": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/FreePeak/db-mcp-server"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add db -- TODO 'See README: https://github.com/FreePeak/db-mcp-server'

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

Anwendungsfälle

Praxisnahe Nutzung: db-mcp-server

Run cross-database analysis from Claude

👤 Data engineers ⏱ ~25 min intermediate

Wann einsetzen: You need to pull from Postgres (app) AND MySQL (legacy) in one conversation without switching tools.

Voraussetzungen

config.json with both connections — Repo docs show the shape; store credentials in env refs, not inline

Ablauf

Start the server

Run ./bin/server -t sse -c config.json and confirm both connections come up.✓ Kopiert

→ Server logs 2 connections ok
Query each

From prod (Postgres): users signed up last week. From legacy (MySQL): orders attributed to them. Join in memory.✓ Kopiert

→ Combined dataset

Ergebnis: Cross-system insights without a data warehouse.

Fallstricke

Read-only assumption breaks — agent runs INSERTs — Use DB-level read-only users per connection; don't rely on agent discipline

Kombinieren mit: google-sheets

Manage TimescaleDB hypertables from Claude

👤 Observability / IoT teams ⏱ ~20 min advanced

Wann einsetzen: You want to create/inspect hypertables and continuous aggregates without memorizing Timescale DDL.

Ablauf

Inspect existing hypertables

List all hypertables in metrics DB with chunk interval and row count.✓ Kopiert

→ Table of hypertables
Create a continuous aggregate

Create a 1-hour rollup on sensor_readings grouping by device_id, avg + max + min.✓ Kopiert

→ CAgg created; refresh policy configured

Ergebnis: Timescale ops in minutes, not Google searches.

Explain an unfamiliar schema to get onboarded fast

👤 Engineers inheriting a database ⏱ ~30 min beginner

Wann einsetzen: Day 1 at a new team; you need a map of the DB.

Ablauf

Dump schema

Use schema_<conn_id> on prod. Return tables, FK graph, and row-count order.✓ Kopiert

→ Schema + FK map
Generate a glossary

For each table, infer a 1-line description from column names and sample rows (limit 5 per table).✓ Kopiert

→ Onboarding cheat sheet

Ergebnis: Working mental model in 30 min.

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

db + google-sheets

Export a query result into a shared Sheet for non-tech stakeholders

Query top 50 customers by LTV from prod; write to the 'Top LTV' sheet.✓ Kopiert

db + prometheus

Cross-check DB slow-query findings with DB-level Prometheus metrics

For the slow query found via performance_prod, show the pg_stat_statements metrics from Prometheus for the same window.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
query_<db_id>	sql: str (SELECT)	Read data	1 query
execute_<db_id>	sql: str (DDL/DML)	Writes — guarded by DB permissions	1 query
transaction_<db_id>	statements: str[]	Multi-statement atomic changes	1 tx
schema_<db_id>	table?: str	Discovery / onboarding	metadata query
generate_schema_<db_id>	format: sql\|json	Export for docs/version control	metadata queries
performance_<db_id>	sql?: str	Tune a slow query	plan + stats

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: Your DBs' capacity
Tokens pro Aufruf: Large result sets burn tokens fast — LIMIT aggressively
Kosten in €: Free MCP; DB hosting costs are yours
Tipp: Always add LIMIT / cap output; stream to a file via filesystem MCP for bigger pulls

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: DB-level read-only user recommended for exploration

Credential-Speicherung: config.json references env vars; never commit with inline passwords

Datenabfluss: Only to configured DB hosts

Niemals gewähren: DB superuser to the MCP connection unless absolutely needed

Fehlerbehebung

Häufige Fehler und Lösungen

Connection pool exhausted

Tune pool size in config.json; kill zombie sessions on DB side; verify no runaway agent loops

Prüfen: SELECT * FROM pg_stat_activity (for Postgres)

Oracle wallet auth fails

TNS_ADMIN path must be readable by the MCP process; on mac/linux watch for SELinux/AppArmor

Tool names don't appear for one DB

That connection likely failed to init; check server logs — usually wrong creds or firewall

Alternativen

db-mcp-server vs. andere

Alternative	Wann stattdessen	Kompromiss
postgres-mcp (official)	You only need Postgres	Single-DB
mysql-mcp (community)	You only need MySQL	Single-DB

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen