AI can write code and pass the bar exam, but it still struggles to buy a pair of shoes online. That’s because websites were built for humans, not agents. Most agents that shop for someone today work from a site’s HTML — they look at the page, guess which button does what, click, and try again when they get it wrong. This process is slow, uses a lot of tokens, and something as seemingly innocuous as a theme change can break it. Enter WebMCP: a browser standard from Google that gives AI agents structured tools on a page, like search_products . Instead of hunting for buttons, the agent calls the exact tool it needs directly, making shopping faster, cheaper, and far more reliable. Because WebMCP is still an experimental proposed browser standard in early preview, it’s currently available behind experimental Chrome flags ( chrome://flags/#enable-webmcp-testing ), in Chrome Origin Trials, in some agentic browsers, and across developer environments like Cloudflare Kitesurf . In August, we launched edge implementation of WebMCP in beta. Turn it on, and Cloudflare injects a tiny script at the edge to make those tools available automatically, without site owners writing a single line of code. Commerce. com , a flexible commerce platform built for the age of AI, already uses Cloudflare to run their almost 100,000 domains. So when the preview came out, they asked: Can we turn this on for all of our stores at once? Here’s why Commerce. com wanted WebMCP, how we built edge-level opt-outs to give every merchant control, and what we learned along the way. Why Commerce. com wanted WebMCP
Kristina Pototska, Product Management Director at Commerce. com, explains why this matters for storefronts:
“Merchants keep asking us how they can keep up with agentic shopping. When a shopper asks an agent to find something, merchants want their store to be in the answer. They want to keep the customer, keep control of the checkout, and do it without rebuilding their site. WebMCP helps with all three. The agent gets real tools to search products, check details, build a cart, and get a checkout link, so it doesn’t have to guess its way around the page. The human shopper stays on the merchant’s site, and the merchant keeps the relationship. We wanted to turn this on in a secure way, and without asking merchants to edit their theme or do anything by hand. That’s where the Cloudflare partnership worked perfectly. WebMCP also works side by side with our server-side MCP , and together they cover the different ways people shop with agents. Server-side MCP supports agents that connect to a store directly, like an assistant helping someone shop across several sites. WebMCP supports agents that work in the shopper’s browser. It’s the same set of shopping tools in both cases, so merchants don’t have to choose between the two or manage them separately.” Under the hood, this integration relies on two key principles. First, the WebMCP tools execute directly inside the shopper’s active browser session on the storefront’s domain, ensuring the agent sees the same prices and cart. No credentials go to a third party, and the visit still happens on the merchant’s site. Second, Cloudflare serves as the edge delivery layer for Commerce. com’s backend MCP server, proxying tool definitions and actions unchanged so merchants maintain full control over their tool logic. What a shopper’s agent sees
When visiting an enabled Commerce. com storefront, an AI assistant no longer has to guess how to navigate the site. Instead, it can instantly discover tools via WebMCP. Suppose you tell your agent: "Find me a waterproof trail running shoe under $140 in size 10 and add it to my cart."…