AWS Agentic DevOps with the EKS MCP Server

21 snips

Jul 22, 2025

Rajdeep Saha, a Principal Solutions Architect at AWS, shares insights on AI agents and the innovative MCP server for EKS. He highlights how AI can automate Kubernetes cluster creation with just a simple command. The conversation covers the security implications of AI managing AWS resources and the importance of the Model Context Protocol for dynamic tool usage. They also discuss the challenges of local models versus foundational models and the future of AI collaboration in DevOps, showcasing the potential for improved deployment efficiency and intelligent systems in cloud management.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

AI-Powered EKS Management

AWS's MCP server for EKS combines creation, deployment, and troubleshooting tools into one AI-driven experience.
It allows managing Kubernetes clusters using plain English without needing kubectl or manual YAML writing.

ADVICE

Control AI Agent Permissions

Use fine-grain controls in AI agents to limit file reading, writing, and command execution.
Avoid enabling unsafe commands like unrestricted file deletion unless you are experienced and cautious.

INSIGHT

Use Markdown for AI Memory

Saving project context as markdown files helps AI agents maintain long-term memory across sessions.
This approach enhances continuity and accuracy of AI-driven project assistance.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Bret and Nirmal are joined by Rajdeep Saha from AWS to discuss AI agents and the MCP (Model Context Protocol) standard. In this episode, they explore how AI can manage infrastructure with ease and demonstrate creating Kubernetes clusters with a single prompt.

🙌 My next course is coming soon! I've opened the waitlist for those wanting to go deep in GitHub Actions for DevOps and AI automation in 2025. I'm so thrilled to announce this course. The waitlist allows you to quickly sign up for some content updates, discounts, and more as I finish building the course.
https://courses.bretfisher.com/waitlist 🍾

We demonstrate AWS's new MCP server for EKS, showing how AI agents can create Kubernetes clusters and deploy applications with simple English prompts. Using Claude Sonnet 4 through the Cline VS Code extension, Raj creates an entire EKS cluster with CloudFormation, deploys a workload, and demonstrates how the AI automatically troubleshoots and fixes deployment issues - all without touching kubectl or writing YAML manually.

We explore the Model Context Protocol (MCP) standard and how it enables AI agents to dynamically discover and use tools, from AWS services to cost calculators. We discuss the security implications of giving AI write access to AWS accounts, the challenges of context window management, and why local LLMs struggle with complex agentic workflows compared to foundational models like Claude.

We cover emerging standards, particularly Google's Agent-to-Agent (A2A) protocol that was recently donated to CNCF. This complements MCP by standardizing how agents communicate with each other, potentially leading to agent marketplaces where specialized agents can collaborate on complex tasks.

We stress the need for proper security guardrails, best practices, and organizational readiness. As Raj puts it, "Gen AI is an awesome white horse, but you still need Gandalf to ride it."

Looking ahead, we predict rapid evolution in agentic frameworks, multi-agent support, and standardized authentication. For DevOps professionals, the bar is rising - tasks that once took a week may soon be expected in two days with AI assistance. It is becoming crucial to understand these tools before they reach mainstream.

Check out the video podcast version here: https://youtu.be/dAkNUoZ_xtw

Creators & Guests

Bret Fisher - Host
Beth Fisher - Producer
Cristi Cotovan - Editor
Nirmal Mehta - Host
Rajdeep Saha - Guest

(00:00) - Introduction
(05:28) - Why Use Cline with VS Code?
(15:16) - Security and Best Practices
(17:01) - MCP "Marketplaces"
(24:59) - Understanding MCP Endpoint Calls
(26:28) - AWS Account Communication and Tool Access
(26:55) - Cost Estimation with Serverless MCP
(27:58) - Agentic Systems and Iterative Feedback Loops
(30:18) - Deploying and Debugging with EKS MCP Server
(32:56) - Challenges with LLMs in Troubleshooting
(39:47) - Agent to Agent Communication (A2A)
(46:47) - Anticipating Future Developments
(47:24) - Practical Advice for Cloud Engineers
(51:17) - Amazon Q
(58:22) - Conclusion and Final Thoughts

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 ★