When Al Agents go Rogue: What you're Missing in your MCP Security
No Fluff, Just Real-World Threats
This isn’t your typical marketing webinar. We cover what Agentic AI actually looks like in production, how MCP servers work to broker instructions, and what kind of new threats are emerging.
Agentic AI isn’t coming. It’s already here. Autonomous agents are now operating in production environments, reasoning, remembering, and taking real actions across your systems. They’re not just generating content. They’re triggering workflows, modifying records, and making decisions. And they’re doing it over APIs.
For CISOs, this represents a major shift in the risk landscape. You’re now dealing with a new layer of autonomous behavior, powered by Model Context Protocol (MCP), that is invisible to most current security tools.
In the session, we cover:
- What Agentic AI is and how it’s changing your risk profile
- Practical attack scenarios against AI agents and MCP servers
- Why and how API traffic is exploding and going largely unmonitored
- How Salt is uniquely positioned to help you see and secure this new API fabric
- What actions you can take now to protect your organization
Whether you're hands-on in security or responsible for the broader strategy, this session will give you real, actionable insights—not marketing slides.
Speakers:
- Roey Eliyahu, CEO & Co-Founder of Salt Security
- Aviad Carmel, Principal Researcher & Security Architect of Salt Security