BigQuery Data Analytics Skills

[!NOTE] Currently in beta (pre-v1.0), and may see breaking changes until the first stable release (v1.0).

Developers can effortlessly connect, interact, and generate data insights with BigQuery datasets and data using natural language commands.

[!IMPORTANT] We Want Your Feedback! Please share your thoughts with us by filling out our feedback form. Your input is invaluable and helps us improve the project for everyone.

Table of Contents

• Why Use the BigQuery Data Analytics Extension?
• Prerequisites
• Getting Started
  • Antigravity
  • Claude Code
  • Codex
• Installing via a compatible Agent Plugins client
• Authenticating via Application Default Credentials (ADC)
• Usage Examples
• Available Tools
• Generating Skills Instead
• Additional Extensions
• Troubleshooting

Why Use the BigQuery Data Analytics Extension?

• Natural Language to data analytics : Find required BigQuery tables and ask analytical questions in natural language.
• Seamless Workflow: Stay in your CLI. No need to constantly switch contexts to the GCP console for generating analytical insights.
• Run advanced analytics : Generate forecasts, run a contributions analysis using built-in advanced skills.

Prerequisites

Before you begin, ensure you have the following:

• One of these AI agents installed
  • Antigravity
    • Antigravity CLI version v1.6.0 or higher
    • Antigravity 2.0 version v2.0.0 or higher.
  • Claude Code version v2.1.94 or higher.
  • Codex v0.117.0 or higher.
• For Claude Code: Enable the Google Cloud BigQuery connector (under Claude Settings > Connectors).
• A Google Cloud project with the BigQuery API enabled.
• Ensure Application Default Credentials are available in your environment.
• IAM Permissions:
  • BigQuery User (roles/bigquery.user)
• (Optional) To use BigQuery AI/ML skills
  • Ensure that Vertex AI API is enabled
  • IAM permissions:
    • BigQuery Connection User (roles/bigquery.connectionUser)
    • Vertex AI User (roles/aiplatform.user)

Getting Started

Configuration

Please keep these env vars handy during the installation process:

• BIGQUERY_PROJECT: The GCP project ID.
• BIGQUERY_LOCATION: (Optional) The dataset location.

[!NOTE]

• Ensure Application Default Credentials are available in your environment.

Installation & Usage

To start interacting with your database, install the extension for your preferred AI agent, then launch the agent and use natural language to ask questions or perform tasks.

For the latest version, check the releases page.

agy plugin install https://github.com/GoogleCloudPlatform/bigquery-data-analytics-plugin

agy plugin install https://github.com/GoogleCloudPlatform/bigquery-data-analytics-plugin

claude

/plugin install bigquery-data-analytics@claude-plugins-official

codex plugin marketplace add GoogleCloudPlatform/data-cloud-plugins

codex plugin add bigquery-data-analytics@data-cloud-plugins

codex plugin marketplace upgrade data-cloud-plugins

Installing via a compatible Agent Plugins client

This repository is a valid Agent Plugins (v1) plugin. Any Agent Plugins–compatible client can install it directly using its own built-in plugin command — no extra tooling required — by pointing at this repository:

https://github.com/GoogleCloudPlatform/bigquery-data-analytics-plugin

Beyond harnesses covered by the native install above, compatible clients include VS Code, Cursor, GitHub Copilot, and Kiro. See your agent's documentation for its exact install command.

Set env vars: Set your environment vars as described in the configuration section.

[!NOTE]

• Ensure Application Default Credentials are available in your environment.
• See Troubleshooting for debugging your configuration.

Authenticating via Application Default Credentials (ADC)

If you prefer to authenticate using local Application Default Credentials instead of the BigQuery connector, add the included headersHelper script to your .claude-plugin/plugin.json:

"mcpServers": {
  "bigquery": {
    "type": "http",
    "url": "https://bigquery.googleapis.com/mcp",
    "headersHelper": "./scripts/adc-headers.sh"
  }
}

Ensure you have authenticated locally:

gcloud auth application-default login

Note for Windows users: Command Prompt and PowerShell cannot execute .sh scripts natively. To use the ADC fallback, you will need to run your agent from a Unix-like terminal such as WSL or Git Bash.

Usage Examples

Interact with BigQuery using natural language right from your IDE:

• Find Data:

  • "Find tables related to PyPi downloads"
  • "Find tables related to Google analytics data in the dataset bigquery-public-data"

• Generate Analytics and insights:

  • "Using bigquery-public-data.pypi.file_downloads show me the top 10 downloaded pypi packages this month."
  • “Using bigquery-public-data.pypi.file_downloads can you forecast downloads for the last four months of 2025 for package urllib3?”

Available Tools

The tools come from MCP Toolbox's prebuilt bigquery server, grouped into toolsets:

• data - Use these tools when you need to handle large-scale data exploration and dataset management. Use when users need to find data assets or run SQL at scale. Provides metadata discovery and query execution across the data warehouse.
• analytics - Use these tools when you need to handle advanced data intelligence and predictive tasks. Use when a user asks "why" data changed or needs future projections. Provides automated insight generation and time-series forecasting.

For the full, up-to-date list, see the bigquery prebuilt config in the MCP Toolbox repository.

Generating Skills Instead

The tool-backed skills this plugin used to ship were generated from the same prebuilt toolsets. If your agent lacks deferred tool loading, or you prefer skills, regenerate them with the script in this repository:

VERSION=<toolbox version> ./.github/scripts/generate_skills.sh

Use the toolbox version pinned in mcp.json. A single toolset, without the script:

npx @toolbox-sdk/server@<toolbox version> --prebuilt bigquery skills-generate \
  --name "<skill name>" \
  --toolset "<toolset>" \
  --description "<what it is for>"

The generated scripts call the toolbox through npx, so no binary download is needed. See Generate Agent Skills in the MCP Toolbox repository.

The hand-authored skills in skills/ are unaffected and still ship with the plugin.

Additional Extensions

Find additional extensions to support your entire software development lifecycle at https://github.com/gemini-cli-extensions, including:

• BigQuery Conversational Analytics
• and more!

Troubleshooting

Use gemini --debug to enable debugging.

Common issues:

• "failed to find default credentials: google: could not find default credentials.": Ensure Application Default Credentials are available in your environment. See Set up Application Default Credentials for more information.
• "✖ Error during discovery for server: MCP error -32000: Connection closed": The database connection has not been established. Ensure your configuration is set via environment variables.
• "✖ MCP ERROR: Error: spawn /Users/USER/.gemini/extensions/bigquery-data-analytics/toolbox ENOENT": The Toolbox binary did not download correctly. Ensure you are using Gemini CLI v0.6.0+.
• "cannot execute binary file": The Toolbox binary did not download correctly. Ensure the correct binary for your OS/Architecture has been downloaded. See Installing the server for more information.