Member-only story
WebMC: Google and Microsoft Just Gave Every AI Agent a Front Door to Your Website
Google and Microsoft just co-authored the spec that turns every website into an API for AI agents. The second-order effects here are massive.
Currently, browser agents operate by taking screenshots, parsing the DOM, and guessing which buttons to click. It works about as well as youโd expect. Fragile, expensive, slow.
WebMCP replaces all of that with a single browser API: navigator.modelContext.
Websites register structured tools directly in client-side JavaScript. The agent reads a menu of available actions, calls them, gets structured data back. No scraping. No backend MCP server in Python or Node. The tools run inside the browser tab and share the userโs existing auth session.
Early benchmarks show ~67% reduction in computational overhead compared to visual agent-browser interactions. Task accuracy around 98%.
The Second-Order Effect Nobodyโs Talking About
Today, when a browser agent visits two competing airline sites, itโs guessing at both interfaces equally.
Once WebMCP adoption spreads, the site that exposes structured tools gives the agent a clean, reliable path to complete the task. The site that doesnโt forces theโฆ
