BigQuery MCP

v1.0.0Analyticsstable

BigQuery MCP server for Claude — query any BigQuery dataset in natural language, with built-in SEO analysis tools for GSC bulk export data

suganthans-bigquery-mcp-servermcpai-integration
Share:
35
Stars
0
Downloads
0
Weekly
0/5

What is BigQuery MCP?

BigQuery MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to bigquery mcp server for claude — query any bigquery dataset in natural language, with built-in seo analysis tools for gsc bulk export data

BigQuery MCP server for Claude — query any BigQuery dataset in natural language, with built-in SEO analysis tools for GSC bulk export data

This server falls under the Analytics and Databases categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • BigQuery MCP server for Claude — query any BigQuery dataset

Use Cases

Query BigQuery datasets using natural language.
Analyze SEO data from Google Search Console exports.
Perform large-scale data analysis with Claude.
LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 7, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx suganthans-bigquery-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use BigQuery MCP

Suganthan's BigQuery MCP Server connects Claude and other MCP clients to Google BigQuery, offering 32 specialized tools spanning custom SQL queries, SEO analysis from Google Search Console bulk exports, GA4 traffic attribution, anomaly detection, traffic forecasting, keyword gap analysis, and content cannibalization detection. It is purpose-built for SEO professionals and data analysts who store GSC and GA4 data in BigQuery and want to perform natural-language analysis without writing SQL manually.

Prerequisites

  • Node.js 18 or later installed
  • A Google Cloud project with BigQuery API enabled
  • A service account JSON key file with BigQuery Data Editor, BigQuery Data Viewer, and BigQuery Job User roles
  • GSC bulk export data loaded into BigQuery (for SEO analysis tools)
  • An MCP client such as Claude Desktop
1

Clone the repository and install dependencies

Clone the BigQuery MCP Server repository and install Node.js dependencies.

git clone https://github.com/Suganthan-Mohanadasan/Suganthans-BigQuery-MCP-Server.git
cd Suganthans-BigQuery-MCP-Server
npm install
2

Build the TypeScript project

Compile the TypeScript source to JavaScript.

npm run build
3

Create and configure a Google Cloud service account

In the Google Cloud Console, create a service account and grant it BigQuery Data Editor, BigQuery Data Viewer, and BigQuery Job User roles. Download the JSON key file and note its path.

4

Add the server to your MCP client config

Add the BigQuery MCP server entry to your Claude Desktop claude_desktop_config.json with your GCP project ID and service account key path.

{
  "mcpServers": {
    "bigquery": {
      "command": "node",
      "args": ["/path/to/Suganthans-BigQuery-MCP-Server/build/index.js"],
      "env": {
        "BIGQUERY_PROJECT_ID": "your-gcp-project-id",
        "BIGQUERY_KEY_FILE": "/path/to/service-account-key.json",
        "BIGQUERY_DEFAULT_DATASET": "searchconsole",
        "BIGQUERY_LOCATION": "US"
      }
    }
  }
}
5

Restart Claude Desktop and run a test query

Restart Claude Desktop and ask it to list available BigQuery datasets or run a simple query to confirm the connection.

BigQuery MCP Examples

Client configuration

Full Claude Desktop JSON config for Suganthan's BigQuery MCP Server, including optional GA4 dataset for revenue attribution.

{
  "mcpServers": {
    "bigquery": {
      "command": "node",
      "args": ["/Users/yourname/Suganthans-BigQuery-MCP-Server/build/index.js"],
      "env": {
        "BIGQUERY_PROJECT_ID": "my-seo-project",
        "BIGQUERY_KEY_FILE": "/Users/yourname/.gcp/service-account.json",
        "BIGQUERY_DEFAULT_DATASET": "searchconsole",
        "BIGQUERY_LOCATION": "US",
        "BIGQUERY_GA4_DATASET": "analytics_123456789"
      }
    }
  }
}

Prompts to try

Example prompts leveraging the SEO, GA4, and general BigQuery analysis tools.

- "Which keywords generate the most revenue from organic traffic this month?"
- "Forecast my organic traffic for the next 90 days"
- "Are there any traffic anomalies I should investigate in the last 30 days?"
- "Find keyword cannibalization issues across my top landing pages"
- "Show me CTR benchmarks by position for my top 50 queries"
- "Run this SQL query: SELECT query, SUM(clicks) FROM searchconsole.searchdata_url_impression GROUP BY query ORDER BY 2 DESC LIMIT 20"

Troubleshooting BigQuery MCP

Authentication error: 'Could not load the default credentials'

Ensure BIGQUERY_KEY_FILE points to the absolute path of your service account JSON file. Alternatively, run gcloud auth application-default login to use application default credentials.

Permission denied when querying a dataset

Verify the service account has all three required IAM roles on the GCP project: BigQuery Data Editor, BigQuery Data Viewer, and BigQuery Job User. Grant them in the IAM section of the Google Cloud Console.

SEO analysis tools return no results

The SEO tools expect GSC bulk export data in BigQuery. Follow the Google Search Console bulk data export guide to set up the export pipeline, then set BIGQUERY_DEFAULT_DATASET to the name of your GSC dataset (typically 'searchconsole').

Frequently Asked Questions about BigQuery MCP

What is BigQuery MCP?

BigQuery MCP is a Model Context Protocol (MCP) server that bigquery mcp server for claude — query any bigquery dataset in natural language, with built-in seo analysis tools for gsc bulk export data It connects AI assistants to external tools and data sources through a standardized interface.

How do I install BigQuery MCP?

Follow the installation instructions on the BigQuery MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with BigQuery MCP?

BigQuery MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is BigQuery MCP free to use?

Yes, BigQuery MCP is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

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

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use BigQuery MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides