広告掲載
MCP.so
ログイン

BigQuery MCP Server

@MCP-Mirror

リポジトリ

基本情報

カテゴリ

データベース

トランスポート

stdio

作者

MCP-Mirror

BigQuery MCP Server について

Mirror of

#bigquery#llm#data-communication

BigQuery MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "ergut_mcp-bigquery-server": {
      "command": "npx",
      "args": [
        "@smithery/cli",
        "install",
        "@ergut/mcp-bigquery-server",
        "--client",
        "claude"
      ]
    }
  }
}

BigQuery MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is BigQuery MCP Server?

It is a server that connects LLMs like Claude to BigQuery via the Model Context Protocol, allowing natural language queries to databases. It acts as a secure translator between AI assistants and BigQuery data.

How to use BigQuery MCP Server?

Install via Smithery by running npx @smithery/cli install @ergut/mcp-bigquery-server --client claude or manually by adding a configuration to Claude Desktop's claude_desktop_config.json. Provide your Google Cloud project ID, location (defaults to us-central1), and optionally a service account key file. Then start asking questions in Claude Desktop.

Key features of BigQuery MCP Server

  • Translate natural language questions into SQL queries.
  • Access both tables and materialized views in datasets.
  • Explore dataset schemas with labeled resource types.
  • Enforce a 1GB query limit for safe analysis.
  • Read-only access ensures data security.
  • Integrates with MCP, available in Claude Desktop.

Use cases of BigQuery MCP Server

  • Ask business questions like "top 10 customers last month" without writing SQL.
  • Explore database schema and tables through natural language.
  • Generate ad-hoc reports by chatting with your data.
  • Enable non-technical users to query BigQuery.

よくある質問

1

What LLMs does this server work with?

Currently only Claude Desktop in developer preview.

2

What are the prerequisites?

Node.js 14+, a Google Cloud project with BigQuery enabled, and either Google Cloud CLI or a service account key.

3

How does authentication work?

You can use Google Cloud CLI (`gcloud auth application-default login`) for development or supply a service account key file with `--key-file` for production.

4

Is the data accessed read-only?

Yes, queries are read-only with a default 1GB processing limit

コメント

「データベース」の他のコンテンツ

PostgreSQL Model Context Protocol (PG-MCP) Server

stuzero

540

Neon MCP Server

neondatabase

MCP server for interacting with Neon Management API and databases

617

MongoDB MCP Server

mongodb-js

A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.

1.1K

golfdata.online - Verified Golf Clubs

golfdata.online

Verified golf club data for AI agents: holes, par, address, phone, booking links, facilities, visitor rules and green fees for golf clubs in Spain (Canary Islands and mainland), expanding across Europe. Every fact comes

Neon MCP Server

neondatabase-labs

MCP server for interacting with Neon Management API and databases

617
広告掲載