Running AI MCP Tools on Kubernetes with kagent
Description
Bret and Nirmal explore AI agents in Kubernetes with Eitan Yarmush, Senior Architect at Solo.io. Eitan explains how AI agents work through three simple components (system prompts, LLMs, and tools), and demonstrates the kagent project, which provides a Kubernetes-native way to deploy and manage AI workflows.
🙌 Special Event on Thursday, October 2nd: Learn about Kubernetes Pod Live Migrations (between nodes) with me and Cast.AI, and maybe win our prizes, including AirPods Pro 3!
https://cast.ai/webinars/container-live-migration-bret/
Â
Also in this episode, we cover the Model Context Protocol (MCP), which standardizes how agents communicate with external tools, along with practical use cases like incident response, debugging workflows, and CI/CD integration. Eitan shows how to create an agent through a web interface.
We also address the challenges including security concerns (MCP lacks built-in security standards), cost considerations, and technical limitations like context window constraints.
Check out the video podcast version here: https://youtu.be/JTTqG5SOpWY
Creators & Guests
- Bret Fisher - Host
- Beth Fisher - Producer
- Cristi Cotovan - Editor
- Nirmal Mehta - Host
- Eitan Yarmush - Guest
- (00:00 ) - Intro
- (06:16 ) - Hype vs Reality
- (08:08 ) - Incident Response and Debugging
- (11:26 ) - Defining Agents and MCP
- (17:13 ) - Where Do You Run Agents?
- (20:17 ) - What Problem does kagent Solve?
- (30:45 ) - Authentication and Tool Limitations
You can also support my free material by subscribing to my YouTube channel and my weekly newsletter at bret.news!
Grab the best coupons for my Docker and Kubernetes courses.
Join my cloud native DevOps community on Discord.
Grab some merch at Bret's Loot Box
Homepage bretfisher.com
★ Support this podcast on Patreon ★