If you're building apps that you want to surface as a "hybrid" UX - both conversational _and_ traditional UI - WebMCP gives you an elegant means of building for both agents and humans at the same time.
If you're building an AI app with a conversational front door, Persona helps you build your experience from a great starting point that already works, and we're constantly iterating on it to keep pace with frontier AI experiences. So you can just implement + configure/theme it instead of trying to start from scratch.
Do you think the new WASI 0.3 stuff will help? I hope so. I'm always super impressed when I see an awesome WASM + WebGPU implementation that doesn't spin up my laptop fan.
For canvas/WASM-style apps, I actually think explicit agent-facing APIs become even more important. If the UI is mostly pixels, an agent has less useful DOM/accessibility structure to infer from. WebMCP gives the app a way to expose semantic actions like “create shape”, “select layer”, “export”, “run simulation”, etc. regardless of whether the UI underneath is React, vanilla DOM, canvas, or WASM.
I agree re: getting closer to the metal - it seems like HTML is having a big resurgence as agents are very productive at producing HTML artifacts which are often 'good enough' for many content use cases, and fortunately Persona works great as an embed in a static site. We spin up demos like that all the time.
It's definitely early - it shipped in the very latest version of chrome just this week, and the spec may still evolve (as a fair warning to early adopters).
You can turn it on for your site via the chrome origin trial, or just install the polyfill.
Our use case with Persona is all about extending existing apps to have "AI assistance" that actually works well, and Persona being the AI assistant you can ship yourself in your site to enhance your app. There's a parallel camp who are interested in adding WebMCP tools to their sites so they can be used effectively by future browser-level agents (e.g. Gemini in Chrome), but that's not a thing today.
Some AI agents can already do best-effort operation of existing websites via naive 'headless browser' approaches, or doing their best to interpret the existing nature of a page by reading the DOM or accessibility tree and trying to submit the forms, but that's flaky and token-inefficient. WebMCP is all about registering those things as explicit, designed tools built for agents. I'd draw a parallel between asking agents to just call existing REST APIs for an app vs intentionally designing MCP APIs for them; the design philosophy is different.
WebMCP's finally at a point where it makes sense to build against it (shipped in latest chrome + good polyfills available), and I've found it a pretty elegant way to extend existing FE apps by just hooking into your existing FE functions instead of having to build an AI assistant as a parallel thing that is ignorant of the user's session, what they're looking at, etc. This makes hybrid AI/app experiences feel much better.
WorkOS is launching auth.md which offers a generic version of this for allowing agents to sign up for services in general, and I think their security approach is a little bit better thought out