WebMCP: Let Websites Declare Tools, Not Get Scraped, So AI Agents Just Work
WebMCP: Teaching Your Website to Talk to AI Agents
WebMCP is a proposed web standard from Google and Microsoft that lets a web page register structured tools an AI agent can call directly, instead of scraping the DOM. It's available as a Chrome origin trial from Chrome 149. The post explains the core shift from scraping to declaring, shows a minimal code example, and walks through a real deployment: Career Copilot, a live agentic career portal with 13 tools that reads resumes, scores real job matches, and gates the only consequential action behind human approval.
The agent isn’t a separate bot logging in with stolen credentials somewhere. It’s calling a function in your open, authenticated tab, using the session you already have.
- sandeepkd
This feels inverted and impractical in so many ways.
On one hand the claims are being made that AI is smart enough to replace software engineers and on other hand the website owners are beings asked to provide information in a certain format to the Agents so they can do their job better. Remember this is the same information that every regular user is able to use.
Secondly if you maintain two versions of information, one for regular humans and one for agents, its just a matter of time before they start to diverge from each other. One can pick up and compare the native app and Browser application for any company, 99% chances are they are not exactly the same.
- mg
> Here’s a book_table tool. It takes a date, a time, and a party size. Call it.
Why not offer a simple form that humans and AI can use alike?
<form action=book_table>
<input type=date name=date>
<input type=time name=time>
<input type=number name=party_size>
<input type=submit value="Book table">
</form>
- dzonga
we already have something better than WebMCP - i.e general APIs.
more impactful work has to be done on the native legacy desktop app scene. that's where most of major companies big or small do their work.
agents automating websites is kinda easy. automating legacy desktop apps that's another issue though there's RPA.
- arjie
This is going to sound incredibly silly but I have every HTMX component expose an AI summary with actions possible and then I have a small copy to AI button on the page which creates a new short-lived access token and copies into a prompt the token, and all the components as text.
When I give this even to relatively small-model agents, they use this initial seed to browse the site and do things very well.
The initial prompt suffices. After that most agents just use the HTML to navigate very well. I suppose I could have that description in an aria label if I wanted but it’s the same.
- stillpointlab
It took me some time to wrap my head around why WebMCP even exists. I was thinking that regular MCP + SSE/Websockets could cover almost all of the uses cases.
One interesting use case for WebMCP is cross-site activities that a browser agent might take. If the data-flow in question involves a heterogeneous set of websites.
This feels like a lifeline for incumbent web SaaS more than anything. Future apps can be architected in ways that do not require WebMCP but massive apps like Salesforce or Workday can't really abandon the decades of accidental business logic embedded in the Web UI flows that make up their project. While those same flows could be data-driven, slapping a WebMCP facade on top of them is just more practical. Instead of forcing incumbents to create an AI-native MCP where they are first class citizens, it is easier to let them sprinkle browser affordances throughout their human-centric front-end and offload the work to the agent.
But for my own part, since I am developing from scratch without that legacy need, I actually think relying on WebMCP might be an anti-pattern. It might be useful for the cross-site use case and it might be useful for reducing latency for purely UI activities (e.g. "filter this list" where all the data is already on the client), but in general my feeling is it is better to have a robust MCP interface for agents.