News Summary
As enterprises race to deploy agentic AI, a fundamental trust problem has emerged. AI agents rarely execute single, transparent actions — a single user prompt can trigger multiple underlying steps across critical network and security systems, many of them invisible and unverifiable to the operator. Compounding the risk, AI systems can misinterpret intent or generate unintended actions. Without visibility and validation at every step, enterprises are forced to choose between AI productivity and operational security.
Versa, the global leader in unified security and networking, today introduced a patent-pending Zero Trust architecture for the Model Context Protocol (MCP), applying Zero Trust principles to AI execution. With this approach, no AI action is implicitly trusted – every agent-generated step is validated against user identity, role-based access controls, and system policies before execution, with explicit human validation based on administrator-defined policies.
As Gartner® noted in a recent report, “AI has introduced a new, high-volume class of digital users in the form of agents that traditional SSE/SASE Platforms were not built to secure.”1
The Zero Trust MCP architecture is delivered within Versa Verbo, the company’s AI-powered operations co-pilot, and is integrated with the VersaONE Universal SASE Platform. Together, they deliver Zero Trust AI execution with AI-powered event correlation, anomaly detection, and guided troubleshooting, enabling enterprises to adopt AI-driven operations in production environments without sacrificing control.
Administrators define policies in advance that determine which agent actions execute automatically, which require human approval, and which are blocked — based on user identity, role, system context, action type, and risk level. Every approved action is logged with full attribution, giving operators visibility, auditability, and policy-driven control without creating bottlenecks in AI-driven operations.
"Enterprise AI is at an inflection point," said Sridhar Iyer, Senior Director, AI and ML, Versa. "Until every agent action can be verified, AI in production can turn into a liability, not an advantage. Versa is solving that head-on, and we believe Zero Trust is the only viable architecture for trustworthy agentic AI."
This announcement represents the next step in Versa’s multi-year AI innovation strategy, which began with the launch of its open-source MCP Server in April 2025, enabling secure access between LLMs and Versa tools and APIs to improve contextual awareness and operational efficiency, and continued with the introduction of agentic capabilities in Verbo in late 2025. Versa will continue to evolve its capabilities, extending from per-action validation toward policy-driven automation and deeper operational visibility as enterprise adoption of AI matures.
Versa Verbo supports SaaS, on-premises, and hybrid deployments, giving organizations control over model selection, data locality, and processing environments.
Availability
Versa Verbo with Zero Trust MCP architecture is available now as part of VersaONE Universal SASE Platform Release 23.1.1. For more information, read the Versa blog, Reimagining NetOps: Operational Intelligence Powered by Versa NLP-based Co-Pilot.
About Versa
Versa, the global leader in unified networking and security, enables organizations to create self-protecting networks that radically simplify and automate their network and security infrastructure. Powered by AI, the VersaONE Universal SASE Platform delivers converged SSE, SD-WAN, and SD-LAN solutions that protect data and defend against cyberthreats while providing a superior digital experience. Thousands of customers globally, with hundreds of thousands of sites and millions of users, trust Versa with their mission-critical networks and security. Versa is privately held and funded by investors such as Sequoia Capital, Mayfield, and BlackRock. For more information, visit https://www.versa-networks.com and follow Versa on LinkedIn and X (Twitter) @versanetworks.
1Gartner, SASE/SSE Platforms Must Adapt to Secure the Rise of Agentic AI and (NHI) Non-Human Identity Access, Charanpal Bhogal, Charlie Winckless, Neil MacDonald, John Watts, December 4, 2025.
Versa Networks, VOS, the Versa logo, and Versa Titan are or may be registered trademarks of Versa Networks, Inc. All other marks and names mentioned herein may be trademarks of their respective companies.