OC3 2026 | The Weakest Link in AI: Hardening MCP Servers with CC with Pawan Khandavilli

This talk by Pawan Khandavilli from the Azure Confidential Computing team explains how confidential computing protects AI workloads, especially Model Context Protocol (MCP) servers. MCP servers aggregate credentials for LLMs and agents, creating security risks. Traditional controls like IAM and container isolation are not enough.

Confidential computing uses Trusted Execution Environments (TEEs), memory encryption, and remote attestation to reduce credential leaks and supply chain attacks. Pawan stresses the need for defense in depth, permission design, and runtime controls for full protection.

Learn more about Azure Confidential Computing: https://msft.it/6058QCenI

#Microsoft #MicrosoftAzure #ConfidentialComputing