WebMCP Is the Most Important Thing Google Announced at I/O 2026 (And Almost Nobody Is Talking About It)

查看原文 / View Original 编辑 / Edit

WebMCP Is the Most Important Thing Google Announced at I/O 2026 (And Almost Nobody Is Talking About It)

WebMCP 是 Google 在 I/O 2026 上发布的最重要技术（但几乎没人讨论它）

Google I/O Writing Challenge Submission. This is a submission for the Google I/O Writing Challenge. Right now, every AI agent that tries to use a website is basically doing this: Take a screenshot, guess what’s on screen, click something and hope, take another screenshot, repeat until it works or gives up. It’s the digital equivalent of reading someone’s lips through a frosted glass window. It kind of works, but it’s slow, expensive, and breaks constantly on anything slightly dynamic — a modal, a lazy-loaded form, a JS-rendered button. 这是 Google I/O 写作挑战的参赛作品。目前，每一个试图使用网站的 AI 智能体（Agent）基本上都在做这些事：截屏、猜测屏幕内容、点击某处并祈祷、再次截屏，然后不断重复直到成功或放弃。这在数字世界里，相当于隔着磨砂玻璃去读别人的唇语。它虽然勉强能用，但速度慢、成本高，而且一旦遇到稍微动态一点的内容（如模态框、懒加载表单或 JS 渲染的按钮）就会频繁崩溃。

Google’s answer to this is called WebMCP — Web Model Context Protocol. It entered a public origin trial in Chrome 149 on May 19, 2026, during the I/O Developer keynote. And I think it’s the most consequential announcement of the whole event — not because of what it does today, but because of what it signals about where the web is going. Let me show you what it actually is, how to use it right now, and why I have real questions about whether it will succeed. Google 给出的解决方案叫作 WebMCP（Web 模型上下文协议）。它在 2026 年 5 月 19 日的 I/O 开发者大会主题演讲期间，随 Chrome 149 版本进入了公开试用阶段。我认为这是整个活动中最具深远意义的公告——不是因为它今天能做什么，而是因为它预示了 Web 的未来走向。让我来向你展示它到底是什么、如何立即使用它，以及为什么我对它能否成功存有疑虑。

What WebMCP Actually Does

WebMCP 到底做了什么

The idea is simple: instead of making AI agents figure out what your website does by staring at it, you tell them explicitly. WebMCP lets you expose structured tools — JavaScript functions and annotated HTML forms — directly to browser-based AI agents. The agent doesn’t scrape. It calls your tool like an API. 这个想法很简单：与其让 AI 智能体通过“盯着看”来推断你的网站功能，不如直接告诉它们。WebMCP 允许你将结构化的工具（JavaScript 函数和带有注解的 HTML 表单）直接暴露给基于浏览器的 AI 智能体。智能体不再需要进行网页抓取，而是像调用 API 一样直接调用你的工具。

There are two ways to implement it: 实现方式有两种：

The Declarative API (for forms) 声明式 API（针对表单）

You annotate existing HTML forms with a data-mcp-tool attribute and a description. The agent reads the annotation and knows exactly what the form does. 你只需在现有的 HTML 表单中添加 data-mcp-tool 属性和描述即可。智能体读取这些注解后，就能准确理解表单的功能。

<form data-mcp-tool="search" data-mcp-description="Search for products by category">
  <select name="category">
    <option value="electronics">Electronics</option>
    <option value="clothing">Clothing</option>
  </select>
  <button type="submit">Search</button>
</form>

That’s it. An agent seeing this form no longer has to guess what the fields mean or what the form does. You’ve told it. 就是这样。当智能体看到这个表单时，不再需要猜测字段含义或表单用途，因为你已经明确告诉了它。

The Imperative API (for JavaScript functions) 命令式 API（针对 JavaScript 函数）

For more complex interactions, you register tools programmatically: 对于更复杂的交互，你可以通过编程方式注册工具：

navigator.mcp.registerTool({
  name: "add_to_cart",
  description: "Add a product to the shopping cart by product ID and quantity",
  parameters: {
    productId: { type: "string", description: "The unique product identifier" },
    quantity: { type: "number", description: "Number of units to add", minimum: 1 }
  },
  handler: async ({ productId, quantity }) => {
    const result = await cartService.add(productId, quantity);
    return { success: true, cartTotal: result.total };
  }
});

An agent calling add_to_cart with { productId: "ABC123", quantity: 2 } will get a reliable result — no screenshot guessing, no DOM parsing, no retries. 当智能体调用 add_to_cart 并传入 { productId: "ABC123", quantity: 2 } 时，它将获得可靠的结果——无需截屏猜测，无需解析 DOM，也无需重试。

Why I’m Genuinely Excited

为什么我感到由衷的兴奋

  1. This is a Google + Microsoft co-project. This is the detail that changes everything for adoption: WebMCP is developed jointly by Google and Microsoft in the W3C Web Machine Learning Community Group. That’s not just a Google standard. It’s an emerging web standard with two of the biggest browser vendors aligned on the spec from day one. Cross-vendor agreement at this stage is rare and meaningful. It substantially increases the chance this becomes a real, lasting part of the web platform.

  2. 这是 Google 与 Microsoft 的合作项目。 这个细节决定了它能否被广泛采用：WebMCP 是由 Google 和 Microsoft 在 W3C Web 机器学习社区组中共同开发的。这不仅仅是一个 Google 标准，而是一个新兴的 Web 标准，两大浏览器厂商从第一天起就在规范上达成了一致。在这一阶段获得跨厂商共识非常罕见且意义重大，这大大增加了它成为 Web 平台持久组成部分的可能性。

  3. The timing is right. Browser agents — AI systems that navigate websites on your behalf — are growing fast. Gemini in Chrome, which will support WebMCP APIs, is one. Others are coming. Right now these agents are all fighting the same brittle DOM-scraping battle. WebMCP gives the web a way to meet them halfway. Implementing WebMCP on your site today is the same category of investment as adding proper aria-label attributes in 2015 or adding og:title meta tags in 2012. It felt optional then. It became table stakes.

  4. 时机恰到好处。 浏览器智能体（代表你浏览网站的 AI 系统）正在快速增长。Chrome 中的 Gemini（将支持 WebMCP API）只是其中之一，未来还会有更多。目前，这些智能体都在进行着同样脆弱的 DOM 抓取斗争。WebMCP 为 Web 提供了一种与它们“半路会合”的方式。今天在你的网站上实现 WebMCP，其投资价值等同于 2015 年添加正确的 aria-label 属性，或 2012 年添加 og:title 元标签。当时它们看起来是可选的，但后来都成了行业标配。

  5. The developer experience is genuinely low-friction. The declarative API requires zero new JavaScript — just HTML annotations. You can expose your most common user flows to agents in an afternoon. The barrier is low enough that “let’s try it” is a reasonable thing to say at a sprint planning meeting right now.

  6. 开发者体验非常顺滑。 声明式 API 不需要任何新的 JavaScript 代码，只需 HTML 注解。你可以在一个下午内将最常用的用户流程暴露给智能体。门槛足够低，在现在的冲刺规划会议上提出“我们试试看”是一个非常合理的建议。

Where I Have Real Questions

我存有疑虑的地方

I don’t want to just be a hype machine, because there are genuine open questions here. 我不想只做一个炒作机器，因为这里确实存在一些悬而未决的问题。

Firefox and Safari haven’t committed. This is the elephant in the room. Mozilla and Apple have not signed on to WebMCP. For a standard to truly succeed on the web, it needs more than Chrome. Right now, if you implement WebMCP, it’s Chrome-only by design. That’s not fatal — lots of meaningful features started as Chrome-only experiments before getting broader adoption. But it’s a real constraint. If your user base is heavy on Safari (mobile web, Apple users), WebMCP tooling won’t work for those agents browsing on Safari. Firefox 和 Safari 尚未承诺支持。 这是显而易见但被忽视的问题。Mozilla 和 Apple 尚未加入 WebMCP。一个 Web 标准要真正成功，不能仅靠 Chrome。目前，如果你实现 WebMCP，它在设计上仅限于 Chrome。这并非致命——许多有意义的功能在获得广泛采用前，都是从 Chrome 的实验性功能开始的。但这确实是一个现实的限制。如果你的用户群大量使用 Safari（移动端 Web、Apple 用户），那么 WebMCP 工具将无法为在 Safari 上浏览的智能体提供支持。

“No headless support” is a meaningful limitation. The official Chrome documentation is explicit: WebMCP requires a browser tab to be open. There’s no support for agents to call your tools in a headless state. This means WebMCP is specifically for in-browser agent interactions — not for server-side automation pipelines that many enterprise workflows rely on. For those use cases, you’d still need a backend MCP server. WebMCP and server-side MCP are complementary, not interchangeable. “不支持无头模式（Headless）”是一个重大局限。 Chrome 官方文档明确指出：WebMCP 要求浏览器标签页处于打开状态。它不支持智能体在无头状态下调用你的工具。这意味着 WebMCP 专门用于浏览器内的智能体交互，而不是许多企业工作流所依赖的服务器端自动化管道。对于那些用例，你仍然需要一个后端的 MCP 服务器。WebMCP 和服务器端 MCP 是互补的，而非可互换的。

The spec is not yet on the W3C official standards track. It currently lives in the W3C Web Machine Learning Community Group — an incubation space, not the full standards process. The path from origin trial to official web standard is long and uncertain. WebMCP could follow the path of Service Workers (proposed → standard → ubiquitous). Or it could follow the path of a dozen other promising origin trials that never made it. 该规范尚未进入 W3C 官方标准轨道。 它目前处于 W3C Web 机器学习社区组中——这是一个孵化空间，而非完整的标准制定流程。从试用阶段到成为官方 Web 标准的道路漫长且充满不确定性。WebMCP 可能会走上 Service Workers 的成功之路（提案 → 标准 → 普及），也可能像其他十几个充满希望但最终夭折的试用功能一样消失。

What I’d Actually Recommend

我的实际建议

If you maintain a web app with forms or user-facing workflows, here’s what I’d do this week: 如果你正在维护一个带有表单或面向用户工作流的 Web 应用，我建议你本周做以下几件事：

Step 1: Enable the flag in Chrome today. Go to chrome://flags and search for “WebMCP”. Set it to Enabled, relaunch, and you can start testing immediately without waiting for Chrome 149. 第一步：今天就在 Chrome 中开启该功能。 前往 chrome://flags 并搜索 “WebMCP”。将其设置为 Enabled 并重启浏览器，你无需等待 Chrome 149 即可立即开始测试。

Step 2: Pick your one most important user flow. Don’t try to annotate everything. Pick the single form or interaction that an agent would most benefit from — a search form, a checkout step, a filter UI. Annotate it with the declarative API. It’ll take an hour. 第二步：挑选你最重要的一个用户流程。 不要试图给所有东西都加上注解。挑选一个智能体最能从中受益的表单或交互——比如搜索表单、结账步骤或筛选 UI。用声明式 API 为其添加注解，这只需要一个小时。

Step 3: Sign up for the origin trial. Visit the Chrome origin trial page and register your domain. 第三步：注册参与试用。 访问 Chrome 试用页面并注册你的域名。

← 返回新闻列表 / Back to news list