{"podcast":{"title":"Agentic DevOps : AI Engineering for Infrastructure","slug":"agentic-devops","podcast_index_feed_id":7351100,"rss_url":"https://feeds.transistor.fm/agentic-devops","website_url":"https://agenticdevops.fm","image_url":"https://img.transistorcdn.com/scfZTdWGzzHd49MpOiduVkac3R3yY0f-h0LBO3yfhQg/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS83MDc2/ZmQxYmZkMjk0NTcx/OTg5MmY2YjBkZjQy/NzYwZS5qcGc.jpg","author":"Bret Fisher","episode_count":11,"summary":"Where LLMs, AI Agents, and MCP tools meet DevOps and platform engineering. How can we humans use non-deterministic, often hallucinating LLMs to automate our infrastructure and help us with the job of software lifecycle management? I’m Bret Fisher, and this is the Agentic DevOps podcast. After the invention of AI Agents and the MCP standard in late 2024, I started this podcast in early '25 with a narrow topic focus… to document and advise how AI Agents, MCP tools, and large language models can be used in the real world for assisting with DevOps automation, platform engineering, and day to day systems operations… a podcast series hopefully without the hand-wavy AI hype or dreams of a pure AI workforce. I'm joined by my co-host, Nirmal Mehta, and expert guests trying to make use of crazy texting robots.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/agentic-devops"},"episode":{"title":"Running AI MCP Tools on Kubernetes with kagent","slug":"running-ai-mcp-tools-on-kubernetes-with-kagent","published_at":"2025-07-09T00:29:47+00:00","page_url":"https://stenobird.com/podcast/agentic-devops/running-ai-mcp-tools-on-kubernetes-with-kagent","show_page_url":"https://stenobird.com/podcast/agentic-devops","url":"https://agenticdevops.fm/episodes/running-ai-mcp-tools-on-kubernetes-with-kagent","audio_url":"https://media.transistor.fm/da7123c0/8b33abdd.mp3","summary":"Explore the intersection of Kubernetes and AI agents through the lens of the kagent project and the Model Context Protocol (MCP). Learn how to manage, deploy, and secure AI-driven infrastructure automation workflows.","meta_description":"Learn how to run AI MCP tools on Kubernetes using kagent. A deep dive into agentic DevOps, security risks, and infrastructure automation.","key_points":["Main idea: AI agents in DevOps consist of three core pillars: system prompts, LLMs, and specialized tools","Practical takeaway: Use kagent to provide a Kubernetes-native way to deploy and manage AI workflows and MCP servers","Failure mode: The Model Context Protocol (MCP) spec lacks built-in security, meaning identity and access management must be handled externally","Technical challenge: Managing the 'context window' and tool sprawl is critical to prevent agent confusion and high token costs","Security risk: Centralized CI/CD pipelines storing API keys for agent tools create significant new attack vectors"],"chapters":[{"start_ms":60000,"title":"Introduction to kagent","summary":"An overview of the kagent open-source project and its role in the Kubernetes ecosystem."},{"start_ms":250000,"title":"The Hype and Anxiety of AI","summary":"Discussing the nervous excitement surrounding the rapid deployment of new AI technologies in production."},{"start_ms":450000,"title":"AI Workflows in Production","summary":"Evaluating real-world use cases for AI agents that actually save time and money."},{"start_ms":640000,"title":"AI Troubleshooting Buddies","summary":"The potential for AI agents to act as automated troubleshooting assistants for infrastructure."},{"start_ms":840000,"title":"The Power of AI Tools","summary":"How tools like Docker and Kubernetes integration make LLM agents powerful and actionable."},{"start_ms":1030000,"title":"The Seven-Layer Agent Cake","summary":"Breaking down the framework layer and how it manages agents and prompts."},{"start_ms":1220000,"title":"Running MCP on Kubernetes","summary":"Deciding where to host MCP tools and the benefits of a Kubernetes-native approach."}],"topics":["Kubernetes","AI Agents","Model Context Protocol","kagent","DevOps Automation","Infrastructure as Code","Cloud Native","AI Security"],"duration_seconds":2604,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/agentic-devops/episodes/running-ai-mcp-tools-on-kubernetes-with-kagent/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/agentic-devops/running-ai-mcp-tools-on-kubernetes-with-kagent.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}