Short: Wardenclyffe Engine has MCP routes for a customer's agent and an operator's agent, 50 tools in all, and every tool checks the caller's permissions first.
Read the full write-up: Wardenclyffe Engine
This is a short cut from We Built a Store That AI Agents Can Shop: Inside Wardenclyffe Engine (8:22).
More shorts from this video
A storefront built for shoppers and AI agents (0:38)
149 findings, 8 real: building commerce software with AI (0:40)
One core, three doors: people, systems and AI agents (0:36)
An AI agent checks out in four calls (0:33)
Your next customer might be an AI agent (0:41)
Transcript
So what can an agent actually do? The engine speaks the Model Context Protocol, MCP, which is the standard way AI assistants call tools. There are two routes. One is for a customer's agent, which can search, build a cart, and work with that customer's own orders. The other is for an operator's agent, which can manage the store. Between them there are fifty tools, and each tool checks the caller's own permissions. An agent can do what its owner is allowed to do, and nothing more. The engine also publishes its own tool registry, so an agent can learn what the store offers without anyone reading the source.
Narration is an AI voice (Azure). The facts come from the linked write-up.


