Google launches BigQuery AI agent connector toolset

Google has introduced a new toolset designed to help enterprises connect their AI agents to data stored in BigQuery, addressing the growing demand for agentic applications. These applications, which operate autonomously, are increasingly popular as they enable businesses to maximize efficiency with limited resources.

Key Features of the Toolset

The toolset includes several tools to facilitate interaction with BigQuery:

• list_dataset_ids: Retrieves all dataset IDs within a Google Cloud project.
• get_dataset_info: Provides detailed metadata about a specific dataset.
• list_table_ids: Lists all table IDs within a dataset.
• get_table_info: Fetches metadata for individual tables.
• execute_sql: Allows users to run SQL queries directly in BigQuery and retrieve results.

Integration Requirements

The toolset cannot be used standalone. Enterprises must integrate it with Google’s open-source offerings:

• Agent Development Kit (ADK): Requires assigning the toolset to an agent created within the ADK framework.
• MCP Toolbox for Databases: Natively supports BigQuery’s pre-built toolset.

Implementation Steps

1. For ADK: Import the toolset from the agents.tools module in a Python environment via the ADK CLI or SDK.
2. For MCP Toolbox: Create an mcp-toolbox folder in the same directory as the ADK application and install the toolbox.

Industry Perspective

Charlie Dai, Forrester VP and principal analyst, highlighted the toolset’s potential:

"Google’s ADK and MCP integration provides pre-built frameworks to connect AI agents directly to BigQuery data. This eliminates custom integration work, reducing development overhead, and enables agents to leverage enterprise context for accurate responses."

Competitive Landscape

Google joins rivals like Databricks, Snowflake, and Teradata, which have also introduced MCP-related offerings to connect AI agents with enterprise data. Google plans to expand the toolset but has not disclosed a timeline.