# Google BigQuery for AI agents. Managed auth, ready-made tools.

> Explore datasets and tables, run SQL queries and insert rows in Google BigQuery on behalf of each of your users.

- Page: https://www.agent200.com/connectors/google-bigquery/
- Category: Search and data
- Authentication: Managed OAuth
- Identifier in code: `google_bigquery`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Google BigQuery, through Agent200. In code: "google_bigquery".
What it does: Explore datasets and tables, run SQL queries and insert rows in Google BigQuery on behalf of each of your users.
Page: https://www.agent200.com/connectors/google-bigquery/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Google BigQuery's own page, through the authorization link Agent200 returns. Never ask a user for a Google BigQuery password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: google_bigquery_list_datasets, google_bigquery_list_tables, google_bigquery_get_table, google_bigquery_run_query. Write tools: google_bigquery_create_dataset, google_bigquery_create_table, google_bigquery_insert_rows. Name "google_bigquery" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/google-bigquery/framework/claude/
   https://www.agent200.com/connectors/google-bigquery/framework/chatgpt/
   https://www.agent200.com/connectors/google-bigquery/framework/claude-code/
   https://www.agent200.com/connectors/google-bigquery/framework/muse/
   https://www.agent200.com/connectors/google-bigquery/framework/grok-bot/
   https://www.agent200.com/connectors/google-bigquery/framework/openai-dots/
   https://www.agent200.com/connectors/google-bigquery/framework/claude-duet/
   https://www.agent200.com/connectors/google-bigquery/framework/hermes-agent/
   https://www.agent200.com/connectors/google-bigquery/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Google BigQuery connector, your agent works with each user's own Google Cloud projects. It can list datasets and tables, read a table's schema, run a SQL query, create a dataset or table and insert rows, using only the tools your project allows.

Google BigQuery is Google Cloud's serverless data warehouse for analyzing large datasets with SQL.

## Google BigQuery tools

- **List datasets** (`google_bigquery_list_datasets`, read): List the datasets in a project.
- **List tables** (`google_bigquery_list_tables`, read): List the tables in a dataset.
- **Get a table** (`google_bigquery_get_table`, read): Read a table's schema and details.
- **Run a query** (`google_bigquery_run_query`, read): Run a SQL query and get the results.
- **Create a dataset** (`google_bigquery_create_dataset`, write): Create a new dataset.
- **Create a table** (`google_bigquery_create_table`, write): Create a table with a schema.
- **Insert rows** (`google_bigquery_insert_rows`, write): Stream new rows into a table.

## Limits you can set

**Turn single tools on or off.** Let the agent explore tables and run queries, and switch off `google_bigquery_insert_rows` so it can never write data.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example reading datasets but not inserting rows. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Google BigQuery

Each end user authorizes their own Google BigQuery account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Google BigQuery account, once.
const connection = await agent200
  .user("user_123")
  .connect("google_bigquery");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Google BigQuery tools

Name the user, the model and the tools. The model decides which Google BigQuery tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "What tables are in the analytics dataset",
    tools: ["google_bigquery"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, on Google's own sign-in page. You never see or store their Google password.

**What access is requested.** The scopes the connection needs, such as viewing BigQuery data or managing BigQuery data, listed on Google's authorization screen. Users can remove the app later from their Google account settings.

## Example requests

- "What tables are in the analytics dataset"
- "Show the schema of the orders table"
- "How many orders did we get per day last month"
- "Create a table for weekly signup counts"

## Guides: Google BigQuery with your AI framework

- [Google BigQuery + Claude](https://www.agent200.com/connectors/google-bigquery/framework/claude.md): Set up Google BigQuery for Claude with Agent200, then check which tools are available to your agent.
- [Google BigQuery + ChatGPT](https://www.agent200.com/connectors/google-bigquery/framework/chatgpt.md): Set up Google BigQuery for ChatGPT with Agent200, then check which tools are available to your agent.
- [Google BigQuery + Claude Code](https://www.agent200.com/connectors/google-bigquery/framework/claude-code.md): Set up Google BigQuery for Claude Code with Agent200, then check which tools are available to your agent.
- [Google BigQuery + Muse](https://www.agent200.com/connectors/google-bigquery/framework/muse.md): Set up Google BigQuery for Muse with Agent200, then check which tools are available to your agent.
- [Google BigQuery + Grok Bot](https://www.agent200.com/connectors/google-bigquery/framework/grok-bot.md): Set up Google BigQuery for Grok Bot with Agent200, then check which tools are available to your agent.
- [Google BigQuery + OpenAI Dots](https://www.agent200.com/connectors/google-bigquery/framework/openai-dots.md): Set up Google BigQuery for OpenAI Dots with Agent200, then check which tools are available to your agent.
- [Google BigQuery + Claude Duet](https://www.agent200.com/connectors/google-bigquery/framework/claude-duet.md): Set up Google BigQuery for Claude Duet with Agent200, then check which tools are available to your agent.
- [Google BigQuery + Hermes Agent](https://www.agent200.com/connectors/google-bigquery/framework/hermes-agent.md): Set up Google BigQuery for Hermes Agent with Agent200, then check which tools are available to your agent.
- [Google BigQuery + OpenClaw](https://www.agent200.com/connectors/google-bigquery/framework/openclaw.md): Set up Google BigQuery for OpenClaw with Agent200, then check which tools are available to your agent.

## FAQ

### Who handles the Google BigQuery OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Google BigQuery.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Google BigQuery connection, never another user's. It cannot reach anything the user or Google BigQuery has not authorized.

### Can I limit what my agent can do in Google BigQuery?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [Tavily](https://www.agent200.com/connectors/tavily.md): Web search built for agents, reached with your Agent200 API key.
- [Exa](https://www.agent200.com/connectors/exa.md): Search the web by meaning, read page contents and find similar pages, reached with your Agent200 API key.
- [Firecrawl](https://www.agent200.com/connectors/firecrawl.md): Scrape pages into Markdown, crawl and map sites, and extract structured data, reached with your Agent200 API key.
- [Brave Search](https://www.agent200.com/connectors/brave-search.md): Search the web, news, images and videos from Brave's independent index, reached with your Agent200 API key.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
