Teleport announces general availability of Secure Model Context Protocol (MCP)

With nearly half of enterprises deploying AI, innovation accelerates security risks, but Teleport’s new solution ensures only trusted AI get access to tools, databases, and apps

OAKLAND, CA – August 5th, 2025 – New findings from Enterprise Strategy Group show nearly half (44%) of enterprises have deployed AI. To help organizations harness AI securely amid this rapid adoption, Teleport has today announced general availability of its Secure MCP solution, which provides security guardrails for AI interactions with databases, MCP servers, and other forms of data. This feature, now available on the Teleport Infrastructure Identity Platform, allows companies to apply the same trust architecture to AI that Teleport already uses to secure human and non-human access to non-AI infrastructure.

The Model Context Protocol (MCP) is an open standard that simplifies the interaction of AI models with tools, databases, or applications through universal rules instead of custom coding each time – much like a USB-C port for LLMs. However, MCP also introduces new security challenges because it wasn’t designed with access control built in, meaning there are no native mechanisms to restrict what data AI models can access or how they can use this. This makes the implementation of controlled and audited data access critical to MCP deployments in order to prevent unauthorized access to data. 

Teleport’s Secure MCP ensures that when LLMs access vital company data, they must adhere to the same strict standards for identity, access control, governance, and audit as all other infrastructure technologies. It achieves this through the Teleport Infrastructure Identity Platform, which includes granular Role-Based and Attribute-Based Access Controls (RBAC and ABAC) that govern what LLMs are authorized to access. Teleport also automatically generates comprehensive audit trails of every session event, which is crucial to ensuring that AI deployments conform to audit and regulatory requirements.. 

“AI is terraforming how software is deployed in organizations," says Ev Kontsevoy, CEO of Teleport. “It shouldn’t require a major public security incident to motivate business leaders to prepare for this impending challenge. Applying the same access control guardrails for AI, humans, and non-human identities accelerates AI adoption while locking in the protection needed to prevent unauthorized access of data. That’s why we launched our secure MCP solution for Teleport, to enable enterprises to confidently unlock AI’s innovation without falling prey to its security vulnerabilities and loopholes.”

A wave of AI agent deployments that touch on core enterprise systems is in process, and identity teams need to be prepared,” said Todd Thiemann, Principal Analyst for Identity Security & Data Security at Enterprise Strategy Group. “Recent Enterprise Strategy Group research showed that data privacy and security for AI agents were major concerns for enterprise security teams. Teleport's Secure MCP solution lays the groundwork for secure agent deployment and enables identity teams to get ahead of the game in securing their AI agent deployments.”

The launch of Secure MCP reinforces Teleport's commitment to helping engineers develop technology more rapidly, without risking company data across their infrastructure. With secure MCP support, Teleport’s trusted computing architecture now extends to LLM workflows driven by machines or users:

• Zero Trust Networking for MCP: only authenticated clients are allowed to interact with MCP servers via always-on encrypted connections.
• Live MCP server inventory: automatically discover and register MCP tools across your hybrid infrastructure.
• Strict Access Control: LLMs access only authorized resources.
• Principle-of-Least-Privilege: Authorization is granted just-in-time, based on task, ensuring LLMs only perform actions explicitly permitted by user roles and do not retain overprivileged access.
• Comprehensive Audit Trails: Every LLM data access attempt—whether successful or denied—is logged.

To learn more about Teleport Secure MCP, visit https://goteleport.com/use-cases/secure-model-context-protocol/

About Teleport

Teleport is the Infrastructure Identity Company, modernizing identity, access, and policy for infrastructure, improving engineering velocity and infrastructure resiliency against human factors and compromise. The Teleport Infrastructure Identity Platform implements trusted computing at scale, with unified cryptographic identities for humans, machines and workloads, endpoints, infrastructure assets, and AI agents. Our identity-everywhere approach vertically integrates access management, zero trust networking, identity governance, and identity security into a single platform, eliminating overhead and operational silos. For more information, visit www.goteleport.com or follow @goteleport.

¹ Source; Enterprise Strategy Group, now part of Omdia, Research Survey, Identity Security at a Crossroads, July 2025.