Governance provides the framework for discovering, securing, and auditing AI agents and their underlying infrastructure at scale. As organizations deploy complex agentic workflows, the Govern section serves as the centralized command center for administrators and security teams to maintain oversight across four critical pillars:
- Visibility:Maintaining a unified Agent Registry to discover agents, endpoints, and Model Context Protocol (MCP) servers across the organization.
- Identity and Access:Defining Agent Identity and deploying Agent Gateways to ensure that every interaction—from the user to the model—is authenticated and policy-driven.
- Security and Compliance:Implementing the AI Security Framework, managing metadata labels for organization, and maintaining a rigorous audit trail of data access and request-response logs.
- Operational Oversight:Monitoring the performance, utilization, and health of models and infrastructure to ensure reliability and cost-efficiency.
Agent Registry, safety, and sharing
Agent Registry
Agent Registry is a centralized catalog that lets you store, discover, and govern servers, tools, and AI agents in Google Cloud.
Policies
Assign identity and IAM policies
Learn how to create policies that govern agentic communication with services.
Configure semantic governance policies
Semantic Governance policies add an additional security layer to ensure agent actions match user intent and organizational constraints.
Agent Gateway
Delegate authorization for Agent Gateway
Learn how to delegate authorization for Agent Gateway to IAP, Model Armor, or your own custom authorization service.
Route Gemini Enterprise traffic through Agent Gateway
Learn how to route Gemini Enterprise traffic through Agent Gateway.
Security
Codelab: Secure cross-cloud agentic AI applications
Learn how to secure your agentic applications in the Securing Cross-Cloud Agentic AI Applications codelab.
