Skip to main content
AmigoFish

Manage zero-trust AI agent identity | AgentOps Unlocked

From Red Hat · · 8 min

The player loads from YouTube only when you click. It uses YouTube's privacy-enhanced mode.

If the video does not play, the owner may have turned off embedding. Watch it on YouTube instead.

Watch on YouTube

Not rated yet

Description

Who's calling your tool server? Learn how AI agent identity management with SPIFFE, SPIRE, and MCP Gateway secures autonomous workflows. In this video, Grace Ableidinger demonstrates how to establish verifiable workload identity and granular authorization for autonomous agents. Learn how Secure Production Identity Framework for Enterprise (SPIFFE) and SPIFFE Runtime Environment (SPIRE) issue short-lived cryptographic identities (SVIDs) based on node attestation, and how mutual transport layer security (mTLS) enforces that identity at the transport layer.

00:00 Who is calling your MCP server? 00:43 The risks of shared API keys 01:17 Introducing SPIFFE and SPIRE 01:42 How SPIRE node attestation works 02:42 Enforcing identity with mutual TLS 03:19 Connecting models as a service 04:00 Inspecting traffic with MCP Gateway 05:09 Installing Kuadrant and Authorino 06:00 Testing read and write agent policies 07:00 Scoping agent permissions per request 07:32 Why identity must live in infrastructure

Explore more AgentOps and Red Hat security tools: 📂 Access the AgentOps GitHub repository → https://red.ht/github-agent-ops 🤖 Learn about Red Hat OpenShift AI → https://www.redhat.com/en/technologies/cloud-computing/openshift/openshift-ai?sc_cid=RHCTG0260000496899

Back to Red Hat · Report a problem