JetStream Launches Verified MCP Governance Layer for Enterprise AI Agents

JetStream helps enterprises safely adopt third-party MCP servers, giving security, risk, and assurance teams one platform to verify server images, control agent permissions, and govern runtime activity SANTA CLARA, CA / ACCESS Newswire / July 13, 2026 / JetStream Security, the security-first AI governance platform, today announced new capabilities to help enterprises safely adopt third-party Model Context Protocol (MCP) servers without introducing unmanaged AI supply chain risk. The launch combines the JetStream Verified MCP™ catalog with the JetStream AI Hub™, giving teams one place to verify and govern MCP and model traffic through a common control point.Enterprises are connecting AI agents to MCP servers that give them access to external tools, data, and workflows, often faster than security teams can vet them - and it is not uncommon that many servers are deployed without approval. Only 17% of organizations are using AI at production scale (UBS Evidence Lab), and the blocker is rarely the technology; It is whether AI agents can be trusted, governed, and audited once they are running in production.As MCP adoption accelerates, many enterprises rely on a growing directory of thousands of third-party servers. But the origins of these servers are often ambiguous, and security teams may struggle to answer basic questions before a server reaches production: what the code actually does, what vulnerabilities it might introduce, and which actions its tools can perform. JetStream takes a different approach. Its curated catalog gives teams access to the broad third-party MCP ecosystem alongside more than 100 JetStream Verified MCP images that are analyzed, hardened, and cryptographically attested before an agent can call them.Each verified image is produced through proprietary semantic scanning that analyzes data flows and code paths to identify risks such as credential leakage, unicode smuggling, and obfuscated malware patterns. JetStream remediates identified vulnerabilities, records the results as tamper-resistant attestations built on open standards, and preserves provenance with every image. The platform also gives teams granular control over individual MCP tools, allowing administrators to enable or disable specific capabilities, so each agent gets only the access its workflow requires.The JetStream AI Hub gives enterprises a unified control point to govern MCP and large language model (LLM) traffic, including authentication, authorization, policy enforcement, and content inspection before and after each call. It discovers shadow MCP servers running outside central oversight, brings them under governance, and maps approved servers to sanctioned agents through JetStream AI Blueprints™. This creates a record when an agent's design, resources, or permissions drift from its approved configuration. Additionally, JetStream acts as an OAuth-aware governance broker, not just a simple token passthrough proxy, enabling secure, auditable, and enterprise-ready access across the agentic AI ecosystem.For security leaders, JetStream provides a runtime control plane to manage the MCP supply chain. For risk and governance leaders, it creates an auditable record of third-party AI risk. Together, these controls help enterprises reduce exposure and let teams adopt AI with greater confidence."Enterprises are no longer asking whether AI agents can be useful; they are asking whether they can trust what those agents do once they are connected to the systems that matter. MCP raises the stakes because every server an agent uses is third-party code, wired into tools, data, and workflows. Our customers agree that that's simply too much uncertainty," said AJ Anand, Co-Founder and CTO of JetStream. "We built JetStream to be the one platform that governs AI instead of five tools bolted loosely together. JetStream brings certainty to MCP Verification and reduces supply chain risks, tracing every action back to an approved owner and policy."AJ Anand further points out, "A directory of servers you have never inspected is not a control. We analyze the code, remove the vulnerabilities, attest the result, and let the teams control which tools an agent can call. That is what quality and breadth together look like in practice."JetStream's MCP capabilities are available now, with additional servers and endpoint coverage rolling out throughout the summer. JetStream will demonstrate the JetStream Verified MCP catalog and the AI Hub at Black Hat USA, Booth 4705, August 3 to 5, 2026, in Las Vegas.About JetStream SecurityJetStream Security is the security-first AI governance platform. The JetStream SAIG Platform™ makes every AI agent, model, workflow, and identity in an enterprise visible, attributed, and governed, continuously and at runtime, across the entire AI estate. JetStream is backed by Redpoint Ventures and the CrowdStrike Falcon Fund. Learn more at jetstream.security.Media contact:Mia Balaban mia@tellny.comSOURCE: JetStreamView the original press release on ACCESS Newswire

Raccontata damorningstar.com