mcp-bigquery-server MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

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

Demo en vivo

Cómo se ve en la práctica

bigquery-server.replay ▶ listo

0/0

Instalar

Elige tu cliente

~/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
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

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

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: mcp-bigquery-server

Answer product/growth questions from BigQuery without writing SQL

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

Cuándo usarlo: You have a question whose answer lives in events tables in BQ.

Requisitos previos

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

Flujo

Discover tables

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

→ Schemas
Ask the question

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

→ Numeric answer with SQL shown
Caveat

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

→ Honest caveats

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

Errores comunes

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

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

Flujo

Configure restricted fields

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

→ 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.✓ Copiado

→ Block on raw read; allow on aggregate

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

Errores comunes

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

Combinar con: gateway

Auto-compile a daily metrics digest from BQ

👤 PMs, founders ⏱ ~30 min intermediate

Cuándo usarlo: You want KPIs in Slack every morning without a BI tool.

Flujo

Define the metrics

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

→ SQL per metric
Run and format

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

→ Slack-ready message

Resultado: Daily metrics without managed BI cost.

Combinar con: notion

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

bigquery-server + notion

Weekly KPI doc

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

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.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
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

Coste y límites

Lo que cuesta ejecutarlo

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

Seguridad

Permisos, secretos, alcance

Ámbitos mínimos: bigquery.dataViewer + bigquery.jobUser on specific datasets only

Almacenamiento de credenciales: Service account JSON in a mounted path; never commit

Salida de datos: Query results go to your LLM provider

No conceder nunca: 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.

Resolución de problemas

Errores comunes y soluciones

PERMISSION_DENIED on dataset

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

Verificar: 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.

Alternativas

mcp-bigquery-server vs otros

Alternativa	Cuándo usarla	Contrapartida
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

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills