Overview

Patrick Riley and Carlos Galan from Auth0 present their approach to securing AI agents through identity management. They demonstrate four key pillars for agent security: AI needs to know who you are, agents must call APIs on your behalf, agents should request confirmation for risky operations, and access should be fine-grained. The session includes a hands-on workshop building an authenticated trading agent with MCP server integration.

Watch the Video

Key Takeaways

  • Agent identity is foundational - without knowing who the user is, agents cannot apply proper security restrictions or authorization policies
  • Token vault enables seamless API access - persist refresh tokens and manage token lifecycles so agents can access upstream services without repeated user authentication
  • Asynchronous authorization prevents dangerous actions - implement approval workflows where agents request user confirmation for risky operations like financial transactions through push notifications
  • Fine-grained scopes control agent permissions - define specific API access permissions that agents can use, preventing over-privileged access to user resources
  • MCP servers can be secured as OAuth clients - Model Context Protocol servers can use dynamic client registration and OAuth flows to securely access protected resources

Topics Covered