Versa applies zero-trust controls to AI agent actions with new MCP architecture

Secure access service edge firm Versa Networks Inc. today introduced a zero-trust architecture for the Model Context Protocol that validates every action an artificial intelligence agent takes inside its network operations co-pilot before that action executes.

The design sits within Versa Verbo, the company’s AI-powered operations co-pilot and is integrated with the VersaONE Universal SASE Platform. Versa is pitching it as a fix for what it calls a trust gap in enterprise agentic AI, where a single user prompt can quietly trigger multiple downstream steps across network and security systems with no real visibility into what the agent actually did.

Under the architecture, no AI-generated action is implicitly trusted. Each step is checked against user identity, role-based access controls and system policies before it runs, with explicit human approval required when administrator-defined policies demand it. Administrators set those policies in advance to determine which agent actions execute automatically, which require sign-off and which are blocked outright, based on identity, role, system context, action type and risk level. Every approved action is logged with full attribution.

“Enterprise AI is at an inflection point,” said Sridhar Iyer, senior director of AI and machine learning at 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.”

The release comes as Gartner Inc. and other analysts warn that traditional secure access service edge and security service edge platforms were not built to handle nonhuman identities. In a December report, Gartner analysts wrote that “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.”

Versa Verbo combines the new zero trust execution layer with AI-driven event correlation, anomaly detection and guided troubleshooting. The company says the goal is to let enterprises run AI-driven operations in production without surrendering the auditability that compliance and security teams require.

The announcement extends a push at Versa around agentic operations. The company released an open-source MCP Server in April 2025 to give large language models secure access to Versa tools and APIs, then added agentic capabilities to Verbo in late 2025. Versa says it will continue moving from per-action validation toward broader policy-driven automation as enterprise adoption matures.

Versa Verbo with the Zero Trust MCP architecture is available now as part of VersaONE Universal SASE Platform Release 23.1.1.

Versa is a venture capital-backed startup that has raised $316 million in funding, including rounds of $84 million in June 2021 and $120 million in October 2022. Investors include Sequoia Capital Operations, Artis Ventures, Mayfield Fund Management, BlackRock Inc., Verizon Ventures, Comcast Ventures, Silicon Valley Bank, Liberty Global Ventures, Princeville Capital, RPS Ventures and Triangle Peak Partners.

Image: Versa