No, you can't understand it until you understand that the world isn't all webshit and not everything is best used via REST.

(Not even webshit is best used by REST, as evidenced by approximately every "REST" API out there, designed as RPC over HTTP pretending it's not.)

Nevertheless, MCP is a “webshit” protocol (even in stdio mode), so if web protocols are unsuitable for your problem, MCP would be as well.

Unfortunately, MCP is not HATEOAS. It doesn't need to be, because it's not web-like. I wish it were.

HATEOAS is great for web-like structures because in each response it not only includes the content, but also all actions the client can take (usually via links). This is critical for architectures without built-in structure — unlike Gopher which has menus and FTP and Telnet which have stateful connections — because otherwise a client arriving at some random place has no indication on what to do next. MCP tackles this by providing a stateful connection (similar to FTP) and is now moving toward static entry points similar to Gopher menus.

I specifically wrote about why pure HATEOAS should come back instead of MCP: https://www.ondr.sh/blog/ai-web