News · curated 5 Jul 2026
Securing agentic AI: What's new in VPC Service Controls | Google Cloud Blog
First reported google.com
Coverage timeline
Single-source advisory — first reported, latest, and curated coincide.
Why it matters
It gives defenders network-perimeter controls to constrain compromised agents and enforce tool-level (MCP) policy, addressing agentic data-exfiltration and tool-abuse risks.
Google Cloud announces new VPC Service Controls capabilities aimed at securing agentic AI workloads, including treating agents as first-class IAM identities in ingress/egress rules, conditional access based on MCP attributes (mcp.toolName, mcp.method, mcp.tool.isReadOnly), and native integration blocking public access to the Gemini Enterprise Agent Platform.