Remember when #APIs were quiet little endpoints that waited politely for humans to click buttons? Yeah, that’s over. Now you’ve got swarms of LLM agents duct-taping tools together like caffeinated interns on Red Bull, firing off recursive calls at 3 a.m., and cheerfully melting your infrastructure while insisting everything is “working as intended.” Observability dashboards are screaming, rate limits are sobbing in the corner, and your security model still thinks it’s guarding humans instead of self-directed toolchains with the attention span of a squirrel and root access. Welcome to the new game: not keeping the stack up, but keeping it from eating itself. In this episode of Pop Goes the Stack, #F5's Lori MacVittie and returning guest Connor Hicks discuss the rapid adoption of MCP and the risks of going too fast without considering security, governance, and supply chain pitfalls. Listen now to take control of MCP tools and AI agents before they take over. Chapters: 00:00 Welcome to Pop Goes the Stack 00:47 What is MCP and why should you care? 02:19 Lessons from history: MCP risks vs. early web exploits 04:12 Governance: Open Source vs. bespoke MCP wrapping 06:25 Least privilege for MCP: Limits as security strategy 08:20 The danger of trusting AI agents with too much access 10:49 Treating MCP servers like toddlers with sticks 12:38 Zero trust and AI agent blast radius 14:09 MCP and business workflows 18:02 Key takeaways: Slow down, strategize, secure Learn how you can stay ahead of the curve and keep your stack whole with additional insights on #AppSecurity, multicloud, AI, and emerging tech: https://go.f5.net/5uh50e6j Check out our DevCentral WebAssembly Unleashed podcast: https://go.f5.net/tymn6gwh More about F5: https://go.f5.net/bnaxajol Read our blog: https://go.f5.net/mnbyuw70 Follow us on LinkedIn: https://go.f5.net/c3oo6ae4

 82      4