Google Launches Data Agent Kit for Cloud Services

The new open-source toolkit provides AI agents with secure access to over 15 Google Data Cloud services.

Updated on Oct. 24, 2026 in Artificial Intelligence

Isometric editorial illustration showing a monolithic pillar made of crystalline database blocks, representing structured cloud data architecture. — Google has launched its open-source Data Agent Kit, allowing AI coding agents to securely access and interpret live schemas across Google Data Cloud. AI Illustration. Upload story photo >

Live Poll

Do you trust AI agents to manage your company's data access automatically?

Google has announced the general availability of its Data Agent Kit, a free, open-source tool designed to bridge the gap between coding agents and Google Data Cloud services. It enables agents to better interpret complex table structures and team data preferences.

Why it matters

Default coding agents often struggle to navigate existing database partitioning and table schemas, limiting their utility in professional environments. This kit solves those issues by providing direct access to live schemas and specific tools.

The toolkit features 37 unique skills and currently integrates with 15 Google Data Cloud services, including BigQuery Graph and Bigtable. It is compatible with VS Code, Cursor, Codex, Claude Code, and Antigravity.

The players

Google

A multinational technology company that specializes in internet-related services and products, including cloud computing and artificial intelligence development.

The details

The kit operates by functioning as an MCP server that exposes live schemas, allowing coding agents to interact with Google Data Cloud services more effectively. It includes built-in guardrails that require user consent for irreversible actions and allows for granular access control via IAM policies.

September 29, 2026: Version 1.0.0 was released.
October 13, 2026: Version 1.1.0 was released.
October 24, 2026: Google announced general availability of the toolkit.

The Tech Race

The kit utilizes the Model Context Protocol to standardize how AI agents interact with external data environments. This moves the industry away from custom, brittle integrations toward a unified framework for AI agent capabilities.

Developers can now preinstall this toolkit in Cloud Shell and Cloud Workstations to streamline database interactions. Users benefit from improved security through IAM deny policies that restrict access to specific, high-risk tools.

The takeaway

This release highlights a growing focus on providing AI agents with governed, secure access to enterprise data. Organizations should prioritize applying read-only service accounts when integrating these agents into their existing infrastructure.