MCP and tool boundaries
Connect tools without making the connection itself a permission to use them.
01 · Read the guide
What Is MCP? The Model Context Protocol, Explained by Someone Who Ships Servers →MCP is the USB-C of LLM tooling: one protocol that lets any model talk to any tool or data source. Here's what it is, why it exists, and how I think about building a server.
One small test
Write down the data a tool reads, the state it can change and the approval each change needs. Test a denied call as carefully as a successful one.
Keep reading
- What Is MCP? The Model Context Protocol, Explained by Someone Who Ships Servers
MCP is the USB-C of LLM tooling: one protocol that lets any model talk to any tool or data source. Here's what it is, why it exists, and how I think about building a server.
- AI Agent Permissions Need a Runtime, Not a Better Prompt
NVIDIA's OpenShell and Sentry put agent permissions outside the model. Here's what the new safety stack can enforce, what remains unproven, and how to test it.
- How to Build a Claude AI Agent (The Way I Actually Did It)
A step-by-step guide to building a real Claude AI agent — from the agentic loop to Cloud Run deployment, written by someone who did it in production.
- How I Built a Multi-Agent System That Runs Itself (And What Almost Broke It)
A practical breakdown of building a real multi-agent system in production — how I orchestrated seven AI agents, what coordination patterns I used, and the three failure modes nobody warns you about.