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

Warum nutzen

Hauptfunktionen

Read-only SQL — no INSERT/UPDATE/DELETE/DDL
Configurable query scan limit (default 1 GB) to avoid runaway costs
Field-level restrictions — list sensitive columns; agent can aggregate but not read rows
Schema exploration with table/view differentiation
Service account JSON or gcloud CLI auth

Live-Demo

In der Praxis

bigquery-server.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": {
    "bigquery-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-bigquery-server"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "bigquery-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-bigquery-server"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "bigquery-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-bigquery-server"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "bigquery-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-bigquery-server"
      ],
      "_inferred": true
    }
  }
}

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "bigquery-server",
      "command": "npx",
      "args": [
        "-y",
        "mcp-bigquery-server"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

{
  "context_servers": {
    "bigquery-server": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-bigquery-server"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add bigquery-server -- npx -y mcp-bigquery-server

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

Anwendungsfälle

Praxisnahe Nutzung: mcp-bigquery-server

Answer product/growth questions from BigQuery without writing SQL

👤 PMs, growth analysts with BQ-backed warehouse ⏱ ~15 min intermediate

Wann einsetzen: You have a question whose answer lives in events tables in BQ.

Voraussetzungen

GCP service account with BQ Data Viewer + Job User — IAM > Create service account; download JSON key

Ablauf

Discover tables

List tables in dataset analytics. Describe events and users.✓ Kopiert

→ Schemas
Ask the question

How many users who signed up in March 2026 triggered the 'aha_moment' event within 7 days?✓ Kopiert

→ Numeric answer with SQL shown
Caveat

Any caveats? Timezone, deletion, test users?✓ Kopiert

→ Honest caveats

Ergebnis: Answers in minutes instead of data-team tickets.

Fallstricke

Running SELECT * on a huge fact table blows the scan limit — Always filter by partition column (often _PARTITIONDATE)

Let a less-trusted analyst explore data without reading PII rows

👤 Data platform teams ⏱ ~30 min advanced

Wann einsetzen: You want to open BQ access to more people via chat without each of them being able to read customer emails.

Ablauf

Configure restricted fields

Add config.json entry restricting fields users.email, users.phone, users.ssn. Agent can only aggregate these, not SELECT them raw.✓ Kopiert

→ Config in place
Test

Run SELECT email FROM users LIMIT 10. Verify it's blocked. Then run SELECT domain, COUNT(*) FROM users GROUP BY domain — verify it works.✓ Kopiert

→ Block on raw read; allow on aggregate

Ergebnis: Safer self-service analytics for the LLM era.

Fallstricke

Regex-based field detection can miss complex aliased SQL — Defense in depth — also use BQ column-level security / authorized views

Kombinieren mit: gateway

Auto-compile a daily metrics digest from BQ

👤 PMs, founders ⏱ ~30 min intermediate

Wann einsetzen: You want KPIs in Slack every morning without a BI tool.

Ablauf

Define the metrics

Define queries for: DAU, signups, revenue, top-3 errors. Each with yesterday / 7-day avg.✓ Kopiert

→ SQL per metric
Run and format

Run all and format as a Slack-ready digest. Include week-over-week deltas.✓ Kopiert

→ Slack-ready message

Ergebnis: Daily metrics without managed BI cost.

Kombinieren mit: notion

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

bigquery-server + notion

Weekly KPI doc

Run my weekly KPI queries and create a Notion page in 'Metrics Weekly' with results + commentary.✓ Kopiert

bigquery-server + gateway

PII-safe access via mcp-gateway + Presidio

Put BigQuery MCP behind mcp-gateway with Presidio; verify customer emails get redacted in results.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen	Kosten
list_datasets		First step to orient	free
list_tables	dataset	Navigate a dataset	free
describe_table	dataset, table	Before querying	free
query	sql: str, max_bytes?: int	Main read tool; limited to 1GB scan by default	BQ on-demand: $6.25 per TB scanned

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: BigQuery job quotas (generous)
Tokens pro Aufruf: Query results can be huge — always LIMIT or aggregate
Kosten in €: Pay GCP by bytes scanned ($6.25/TB on-demand). Configure scan limit in MCP to cap.
Tipp: Filter by partition. A full-table scan on a busy fact table = real money. The MCP's byte limit is your safety net.

Sicherheit

Rechte, Secrets, Reichweite

Minimale Scopes: bigquery.dataViewer + bigquery.jobUser on specific datasets only

Credential-Speicherung: Service account JSON in a mounted path; never commit

Datenabfluss: Query results go to your LLM provider

Niemals gewähren: dataOwner / dataEditor to the MCP's service account

Field restrictions are cooperative guardrails for agents — not a replacement for BigQuery IAM/column-level security.
Developer preview status noted by upstream — verify behavior in your setup before prod use.

Fehlerbehebung

Häufige Fehler und Lösungen

PERMISSION_DENIED on dataset

SA lacks BQ Data Viewer. gcloud projects add-iam-policy-binding ....

Prüfen: gcloud bigquery datasets list

Query exceeds configured byte limit

Add partition filter or column projection; or raise limit if legitimately needed.

Restricted field still appearing in results

Regex match may miss aliased columns — use BQ authorized views for hard isolation.

Alternativen

mcp-bigquery-server vs. andere

Alternative	Wann stattdessen	Kompromiss
Looker / Metabase	You want a BI tool, not chat	Better dashboards; less conversational
postgres MCP via Cloud SQL	Your analytical data is in Postgres instead	Different engine; Postgres doesn't scale like BQ for big aggregates

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen