What is MCP?
Model Context Protocol, an open standard that lets an AI agent call into a business's own systems, checking live data or triggering a defined action, the way it would check availability or pull a menu.
2 min read
MCP is the connection layer specifically. A later revision added a thin way to check who's calling in, but proving what an agent is allowed to spend is still a separate protocol's job entirely. It's strongest today for an operator's own tools, a member of staff's assistant querying their own booking system, and weaker on its own for a stranger's agent trying to book from a business it's never dealt with, which needs identity and payment checks on top. Selfe uses MCP as one piece of a larger chain, not the whole answer.
Good for
An operator's own tools querying their own systems.
Not good for
Proving a stranger's agent is allowed to book or spend. Identity and payment need separate protocols.
What is A2A?
Agent2Agent protocol, a standard for how one AI agent hands a task to another agent clearly enough that the second one can trust it and act on it.
What is AP2?
Agent Payments Protocol, a standard for proving that a real person authorised an AI agent to spend a specific amount, so a business can verify that before it charges anything.
What is UCP?
Universal Commerce Protocol, the checkout protocol that completes a purchase once an AI agent has already been connected, identified and authorised, handing a business back a confirmed order instead of an unverified promise.