Tenable to Vet MCP Servers and Skills Using OpenAI's GPT Cyber Models

Tenable announced the CyberAgents Exchange AI Inspector (Exchange Inspector) on September 3, 2026, as a collaboration with OpenAI¹. It is a security review process covering AI agents, skills, MCP servers and multi-agent playbooks available through the company’s CyberAgents Exchange registry, and it was unveiled at OpenAI’s “Intelligence at Work: Cyber Summit.”

• It combines three things: frontier assessment using OpenAI’s GPT cyber models, skills inspection powered by Tenable One AI Exposure, and expert review from Tenable researchers
• Availability is expected in September, though the press release carries a forward-looking statements disclaimer covering both the timing and the capabilities
• The CyberAgents Exchange launched in August 2026 as an open-source registry and now holds more than 100 community-submitted AI components

Tenable chief product officer Eric Doerr said agentic AI will only reach its potential in the enterprise if security teams can trust the components being introduced into their environments, positioning the combination as a more rigorous way to inspect them¹. When MCP servers and skills get pulled in from outside, adoption tends to run ahead of any settled answer on how to trust the supplier. Attaching a review step to the registry is one answer, but the criteria and how pass/fail is surfaced are not published.

Sources

1. Tenable Uses OpenAI GPT Cyber Models to Help Defenders Inspect Community-Built AI Components - Tenable official press release (September 3, 2026)