Google Cloud Security Blog · November 12, 2026

Organization Policy MCP: inspect inheritance and test constraints before enforcement

Why it matters

Google’s Organization Policy MCP server exposes constraint discovery, effective-policy inspection and policy writes across its resource hierarchy. Gemini can draft CEL constraints and test configurations. The MCP server is generally available, while the linked Gemini testing guide still carries a Preview label. These are resource-configuration controls; effective policy and dry-run results alone do not establish agent authorization or compliance of existing resources.

My takeaway: Separate policy inspection from write permissions. Inspect inheritance and tag exceptions, review the generated CEL, and test allowed and denied configurations before enforcement. Dry-run logs violations but does not block actions; check existing resources separately because new constraints are usually not retroactive. Preserve the previous policy and verify the complete change before calling an update tool.
Keep exploring

More curated notes connected through Agent Security and AI Engineering.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.

OWASP GenAI Security Project · tool

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.