BigQuery MCP Server

@MCP-Mirror

Repository

Basic information

About BigQuery MCP Server

Mirror of

#bigquery #llm#data-communication

BigQuery MCP Server config

Add this server to your MCP-compatible client using the configuration below.

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

BigQuery MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

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.

Frequently asked questions

What LLMs does this server work with?

Currently only Claude Desktop in developer preview.

What are the prerequisites?

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

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.

Is the data accessed read-only?

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

Comments

More Databases MCP servers

Xata MCP Server

The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.

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