Skip to content
Conduit

mcp server

mcp-bigquery

atamaplus-public/mcp-bigquerycommunitylistedunreviewed
Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

  • Node.js 20 or newer
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "atamaplus-public-mcp-bigquery": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-bigquery-server"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 18, 2026

BigQuery MCP Server

Read this in other languages: 日本語

An MCP (Model Context Protocol) server for querying BigQuery data. This allows AI assistants like Claude to directly access your BigQuery data.

Features

  • Execute SQL queries to BigQuery using natural language
  • List datasets and tables
  • View table schemas
  • Execute read-only queries with security controls

Usage

Prerequisites

  • Google Cloud project with BigQuery enabled
  • Locally configured authentication credentials
gcloud auth application-default login

Local Execution

  1. Install dependencies:
npm install
  1. Build the project:
npm run build
  1. Start the server:
npm start -- --project-id YOUR_PROJECT_ID --location YOUR_LOCATION

Installation in Claude Desktop

Add the following entry to your Claude Desktop configuration file (typically ~/.config/Claude Desktop/claude_desktop_config.json):

{
  "mcpServers": {
    "bigquery": {
      "command": "node",
      "args": [
        "/absolute/path/to/dist/index.js",
        "--project-id",
        "YOUR_PROJECT_ID",
        "--location",
        "us"  // For US multi-region datasets
      ],
      "env": {
        "GOOGLE_APPLICATION_CREDENTIALS": "/absolute/path/to/your/credentials.json"
      }
    }
  }
}

Connectivity Test

To verify that the server is working correctly, run:

npm test

This test uses a configuration file for test settings. Follow these steps:

  1. Copy the sample configuration file:

    cp config.sample.json config.json

  2. Edit config.json to match your project settings:

    {
  "projectId": "YOUR_PROJECT_ID",
  "location": "us",
  "testQuery": "SELECT 1",
  "resourceUri": "bigquery://YOUR_PROJECT_ID/YOUR_DATASET/YOUR_TABLE/schema"
}

  3. Run the test:

    npm test

The test will run the following checks:

  • Retrieving resource list
  • Retrieving tool list
  • Executing SQL query
  • Reading resource schema

Configuration

The server accepts the following command line arguments:

  • --project-id: (Required) Google Cloud project ID
  • --location: (Optional) BigQuery location, defaults to 'us-central1'
    • Use 'us' for US multi-region datasets

Limitations

  • Only read-only queries are allowed
  • Default query limit is 1GB of processed data
↑↓ navigate openesc close