Josh talks to Luke Hinds, CEO of Always Further, about MCP and agent security. We start out talking about Luke's new tool, nono which is a sandboxing tool that has AI agents in mind as a use case. We explain what MCP and agents are doing as well as why it's so hard to secure them. It's not impossible, but it's not simple either. We end the show by discussing some of the more human aspects to security and how history may be repeating itself with security folks laughing at new users who don't know any better.

The show notes and blog post for this episode can be found at https://opensourcesecurity.io/2026/2026-03-mcp-agent-luke/