1037: WebMCP is here (and you should care)

Sarah Drasner (0:00)

And I think, Wes, you make a really good point about the multimodality of it. Not everybody's gonna be using the web the same way. Like, we've known this forever. I think some people are like, oh, the web will go away, it'll just be people using it in a headless way. And then people go, no, nothing's gonna change. And I think the truth is, like, these experiences are gonna be done all sorts of ways. Like even a shopping, I'm shopping as like a leisurely activity, then I'm gonna be a human in the loop in that activity because that's part of the point. But if I'm just trying to get some shirts for my son that he knows the size of and he knows what he wants, then that, you know, I'm okay with an agent doing that for me.

Scott Tolinski (0:46)

Welcome to Syntax. Today we're talking about WebMCP. We got two folks from Google here to talk about WebMCP. And I personally am really excited about this. It's starting to make its way into clients. And I don't think a lot of people really understand what it is or as a developer, how you should be integrating this into your site. If this becomes a thing that everybody implements. So I'm stoked to talk about it with me. We have Dominic Farolino and Sarah Drasner. They are both from Google working on Chrome. Most people listening to this, I would say everybody listening to this episode knows what an MCP and MCP server is where everyone slapping them into their agents.

Can you just give us a rundown of like what is WebMCP and how is that different?

Sarah Drasner (1:28)

Yeah. I mean, I think people get confused a little bit because of the name. WebMCP is on the client, not the server, and a lot of the similarities are when we are thinking about the principles, like exposing tools to agents, things like that. But they're actually pretty dissimilar. The governing bodies are dissimilar. One is the Agentic AI Foundation in Linux. That's the MCP. For WebMCP, it's W3C like other standards bodies.

For WebMCP, you are really only working on it on the client, but that doesn't mean that it can't negotiate or create server actions, like kickoff arrest or GraphQL API interaction. And then also the way that people are using it agentically, you do have headless scenarios that you can use WebMCP. But we're also thinking about a new surface area of co-browse. And co-browse is where we're spending a lot of time, which is when you have like a human and agent on the loop collaborating on the web experience together. Dom, is that?

Dominic Farolino (2:28)

Yeah, no, I think that was perfect. I think the way I try to describe it to people is, when you give like MCP tools, traditional MCP tools to your agent, it allows you to just enable the agent to do better capabilities inside the chat. But we don't have a really like an MCP for UI, like for like using the site. Like I'm on Google Sheets, I want to do this complicated thing in the UI. I can't remember where all the 10 clicks that the functionality is hidden behind. Sorry, my cat's in the background here.

And so like I want to be able to talk to my agent and say like, okay, I really want to like add conditional formatting to this column and like can you do that for me? Like if we've ever seen agents interact with websites like DOM and UI right now, it's like really, really slow. They're like screenshotting.

Scott Tolinski (3:12)

It sucks, it's awful.

Dominic Farolino (3:13)

It's such a terrible experience. It's expensive actually too, right? It reenters the inference loop every time you got to click a button and do anything.

But all the, the agent is thinking in terms of sort of atomic tasks. I want to add a video track to this YouTube editor, I want to do something in this column at Google Sheets. All that code actually exists in the client. WebMCP is finally a way to let the agent get access to it and actually get to that code and translate its atomic tasks that it's thinking of into actual tasks at the platform or side that the client app is capable of handling.

Scott Tolinski (3:45)

Yeah.

If you look at where we're at right now, like you said, if you have an MCP server for something and you want to interact with it, you're typically just getting like chat back and forth. In a lot of cases, that's awful. So now we have like MCP UI where you can have these little widgets that make their way into the chat. And that's okay in some cases, but in some cases, you know what the best UI is? The existing app is the best UI for that.