The Google Cloud Data Agent Kit is a unified development interface for data scientists, engineers, and app developers on Google Cloud. It integrates core Google Cloud data services—including BigQuery, Dataflow, Managed Service for Apache Spark, Spanner, AlloyDB, and Cloud SQL—directly into your IDE.
By bringing these services into your development environment, the Data Agent Kit eliminates the need to switch between the Google Cloud console, command-line tools, and your IDE.
Key Features
The Agent Kit streamlines complex data workflows through several key functional areas:
- Data discovery and exploration: Connect to and explore your data on Google Cloud. Query and analyze your data in Python and SQL. Ask questions about your data in natural language.
- Data pipeline development: Build, test, and deploy production-ready Apache Spark, BigQuery or Dataflow data engineering pipelines.
- AI and machine learning: Explore and clean data and use it to train and deploy ML models.
- Agentic skills and tools: Leverage built-in AI skills and tools to automate repetitive tasks and accelerate development.
Supported Services
The Data Agent Kit provides a centralized interface for the following Google Data Cloud services:
| Category | Supported Services |
|---|---|
| Analytics and governance | BigQuery, Dataflow, Managed Service for Apache Spark, Managed Service for Apache Airflow, Knowledge Catalog |
| Databases | AlloyDB for PostgreSQL, Cloud SQL, Spanner |
| Storage | Cloud Storage |
Security Reminder: Agent Environment Hardening
Your agent can execute tools and commands on your behalf. Protect your Google Cloud resources by enforcing The Principle of Least Privilege across all CLIs, MCP servers and other resources available to your agents.
- Service Accounts: Use service accounts instead of end user credentials to access Google Cloud resources.
- Limited Permissions: Assign roles with limited permissions to the service account that you're using for authentication.
- Principal Access Boundary policies: Prevent unwanted cross-org agent
access by using
Principal Access Boundary policies
to scope your agent to projects you intend it to access.
- Include a condition in the policy binding to ensure that the policy only applies to the service accounts that you intend to restrict.
For more information, see Mitigate indirect prompt injection risks from Google Cloud MCP.
Feedback
To report a bug or request a feature, please use this feedback form.
Terms
The Data Agent Kit is subject to the "General Software Terms" of the Google Cloud Service Specific Terms, available at https://cloud.google.com/terms/service-terms.