Browser agents at Huawei
I spent four months at Huawei researching whether WebMCP is a worthwhile standard for browser agents, and how an agent should be built to use it. I drove the experimental work, from proposing questions and approaches to implementing them and working through the results.
WebMCP lets a website expose actions an agent can call through its forms and JavaScript. Those actions can depend on the page the agent is on.
Imagine an issue tracker on something like GitHub: the issues page could offer tools for creating and managing issues, while the pull requests page offers a different set. The tools don't all have to be available at once.
I worked on both: what capabilities a page should expose, and how an agent should discover and use them. I built tools for pages on some sites we chose and adapted open-source agents to compare methods of allowing the agents to interact with the tools.
When a comparison finished, I went through the runs: where were the gains? Where were the regressions? What was the agent doing differently? I looked at success and efficiency, and used what I found to propose the next experiments.
I also built benchmark queues so the fleet of workstations we had would stay busy overnight, served local models, and tracked down browser, session and model-serving failures when runs stopped.
I'm not personally betting that tools will replace page observation. My expectation is that small local models will get extremely good at difficult computer-use tasks. I think some of the work I did will become outdated quickly. I learned a lot doing it anyway.
In the meantime, WebMCP may be a good way to make web agents usable for people, for cheap and fast. I see it as an interim approach. Let's make products that users can enjoy now. That's the idea.