AI agents are moving into production fast. They read enterprise data, call tools, and take actions across business systems. That creates a new problem: an agent can be fully authenticated and authorized and still be manipulated into doing the wrong thing.
Google Cloud’s Gemini Enterprise gives enterprises a central control plane for agents. Check Point extends that control plane with AI-specific risk assessment and real-time, context-aware protection. This post details where Check Point integrates and what it looks like for a security team.
Google Cloud’s direction with agent orchestration, registries, and gateway layers signals a clear design pattern: centralized AI control planes are becoming the preferred way to build scalable, secure agentic systems. In July, Google Cloud announced enhancements to Gemini Enterprise with several new features designed to secure, audit, and centralize agents including:
- Agent Registry: A single glass pane view of all agents built across an organization. It serves as a single library for all the AI agents, servers, and connections across an organization, enabling administrators to monitor agent sprawl
- Agent Gateway. A central control point to secure and govern all interactions across an organization’s agent ecosystem, allowing for the enforcement of granular access controls as well as safeguards against prompt injection, tool poisoning, and data leakage.
Together they answer the questions security teams have been asking since the first agent shipped: What agents do we have, what can they reach, and where can we enforce a decision?
Where Check Point integrates
Check Point AI Agent Security integrates with both services, plus agent observability, to protect every interaction in the agentic stack.
- Pre-workflow risk posture (Agent Registry). Check Point observability reads the registry to surface risk posture on agents and their connected tools before workflows begin. Teams see risky configurations, permissions, and Model Context Protocol (MCP) connections and can set boundaries before agents move into production.
- Prompt defense (Agent Gateway). All user-to-agent and Agent2Agent (A2A) traffic is vetted by Check Point prompt injection defenses, embedded as Agent Gateway service extensions. Inspection happens inline, before the agent acts.
- MCP security (Agent Gateway). MCP tool calls are catalogued, and permissions are vetted against agent identity. Indirect prompt injection carried in MCP server content is blocked in real time.
The key design choice: Check Point evaluates not just whether an agent has permission to perform an action, but whether that action is appropriate given the full context of the interaction. Prompts, responses, tool calls, and multi-step behavior are all in scope.
What this looks like for a security team
The integration is organized around three questions many security teams seek to answer:
Where are my agents? Agent Registry gives a centralized view of the agent estate: agents, components, tools, and MCP connections. Check Point adds posture assessment and policy controls on top, so teams know which agents introduce risk and can set boundaries before production.
Can my production agents be protected? An attacker uses prompt injection to steer an agent into calling an approved tool for an unintended purpose. Check Point, in line with Agent Gateway, assesses the input, the tool response, and the intended action together, and blocks the unsafe step before execution.
Can sensitive data be kept inside? Agents touch enterprise data on every turn. Check Point inspects interactions at the gateway to identify sensitive data and how it is being used, and enforces policy before information is returned, transferred, or handed to a downstream tool.
Built for production scale
The runtime engine behind this integration already protects agent traffic at scale. At Dropbox, it secures millions of daily AI interactions with 99.8% of real-world threats blocked, sub-40ms average latency, and a production false positive rate under 0.5%. At Nubank, it secures over 1M transactions per app per day across 100+ languages at a 0.01% false positive rate. Deployment took minutes, with zero code changes to customize policies.
Speed matters on a gateway. Security that adds latency or noise gets turned off. Security that is fast and precise stays on.
Getting started
Check Point is a launch security partner for Google Cloud Gemini Enterprise, announced at Google Cloud Next ’26 and powered by the Check Point AI Defense Plane for employees, applications, and agents. Customers on Google Cloud can discover their agent estate, assess risk, set policy, and inspect agent behavior at runtime, while development teams keep building.
