What do you mean, it can't run multiple monitors? I thought it lets you pop out windows free standing, no concept of monitor at all.
"Ensemble (formerly MacCast, before the lawyers had something to say about it) bridges windows from your Mac directly into visionOS, letting you move, resize, and interact with them just like you would with any other native app. It's wireless, like Mac Virtual Display, but without the limitations of resolution or working in a flat plane."
And this is a quite hard limitation, since the Mac has to actually render those windows and then stream them to the goggles over radio. So, without quite a bit of magic, you have a limited amount of pixels the Mac can draw and send.