BigQuery Data Analytics plugin
An official Google Cloud plugin: the agent finds BigQuery tables, writes SQL and builds forecasts from natural language questions.
- 53 ★ on the repository
- Last commit
- Apache-2.0
Broad access
Why this level
- The agent runs SQL in your Google Cloud project and queries are billed.
- Access uses your account permissions and the BigQuery User role.
- Table data reaches the model context.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/bigquery-data-analyticsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- The agent runs SQL in your Google Cloud project and queries are billed.
- Access uses your account permissions and the BigQuery User role.
- Table data reaches the model context.
This is third-party code. Review the repository files before installing.
What it does
The plugin connects BigQuery through the built-in `bigquery` MCP server and a set of analytics skills. The user asks in plain words: find tables about PyPI downloads, show the ten most downloaded packages this month or forecast a package for several months ahead. Tools are split into two sets: `data` handles discovery and running SQL, `analytics` generates insights and forecasts time series. It works in Claude Code, Codex and Antigravity, plus clients that follow the Agent Plugins standard such as VS Code, Cursor and GitHub Copilot. The Google Cloud project is in beta and may change before 1.0. Advanced AI and ML skills need Vertex AI.
Who it is for. Analysts and developers with a Google Cloud project who want to query BigQuery data from a terminal or IDE.
Good fit when
- Find tables on a topic in the `bigquery-public-data` public datasets.
- The agent computes a top 10 from a table for a month without leaving for the GCP console.
- A time series forecast is needed, such as package downloads.
- You want to know why a metric changed through contribution analysis.
Not a fit when
- The data does not live in BigQuery.
- There is no Google Cloud project or BigQuery User role.
- Queries cannot be sent to a Google cloud service.
Example request
Find tables about PyPI downloads in bigquery-public-data and show the top 10 packages this month.Limitations
You need a Google Cloud project with the BigQuery API enabled, the `roles/bigquery.user` role and available Application Default Credentials. AI and ML skills also need Vertex AI and the `roles/bigquery.connectionUser` and `roles/aiplatform.user` roles. Environment variables are `BIGQUERY_PROJECT` and an optional `BIGQUERY_LOCATION`. The project is in beta and breaking changes are possible. SQL runs in your project and is billed under BigQuery rules, so approve costly queries before they run.
How to disable. Disable the plugin with the Claude Code plugin commands, then revoke the BigQuery connector access and remove local Application Default Credentials if you no longer need them.
FAQ
How do I install the plugin in Claude Code?
Enable the Google Cloud BigQuery connector in Claude settings, set `BIGQUERY_PROJECT` and run `/plugin install bigquery-data-analytics@claude-plugins-official`.
How do I install it in Codex?
Run `codex plugin marketplace add GoogleCloudPlatform/data-cloud-plugins`, then `codex plugin add bigquery-data-analytics@data-cloud-plugins`.
Can I sign in without the connector?
Yes, through Application Default Credentials. Add a `headersHelper` pointing to `./scripts/adc-headers.sh` in `.claude-plugin/plugin.json` and sign in locally with `gcloud auth application-default login`.
Which toolsets exist?
Two: `data` for discovery and running SQL, `analytics` for automated insights and time series forecasts.
Does it work on Windows?
Yes, but the ADC fallback uses an `.sh` script that Command Prompt and PowerShell cannot run, so launch the agent from WSL or Git Bash.
Discussion
No questions or reviews yet.
Related
PluginsA Google Cloud plugin catalog for databases and analytics: AlloyDB, Spanner, Bigtable, Firestore, Cloud SQL and Looker.
A Google plugin for Claude Code, Codex and Antigravity: Looker data queries, dashboards and LookML in plain language.
A Google plugin for Gemini CLI, Claude Code and Codex connects the agent to PostgreSQL: schemas, queries, indexes and query plans.
The Dex plugin: an agent explores a database, builds dbt models and a semantic layer and tracks schema drift under cost control
Monte Carlo plugin for Claude Code and Cursor: table checks before queries, data incident triage and monitor creation.
Official Databricks skills guide coding agents through data work, Lakeflow jobs and resource deployment on the platform.
README in short
The repository covers installation in Antigravity, Claude Code and Codex, authentication setup and two toolsets. A troubleshooting section is included.