Brooks McMillin - Infrastructure Security Engineer

A Claude Code session on my internal monorepo confidently paged through a 156-line Python file.

The gap between OAuth scopes and autonomous agents, and one way to close it# When you put an LLM agent in charge of calling MCP tools on your behalf, OAuth gets you about 70% of the way there and then quietly stops.

How this talk started# I told my AI reviewer to ignore three CVEs.

If you've deployed an MCP server past your own laptop, you've had the auth conversation with yourself.

If you run authenticated remote MCP servers with Claude Code, you've probably fought this.

I gave a talk at [un]prompted earlier this month about what it actually takes to run LLM agents as daily drivers without getting burned.

Introduction# My previous post on defense in depth for AI-assisted development covered what safety layers to use when coding with LLMs and why they matter.

TL;DR.

TL;DR.

Introduction# Bianca is a (fictional) developer who wants to use an LLM to help her generate a script to download some of the latest LLM models from HuggingFace, a popular model hosting service.