📄 中文摘要
Google 在上周的 Chrome 146 Canary 中发布了 WebMCP，这是一个由 Google 和 Microsoft 共同构建的提议 W3C 标准。WebMCP 允许网站通过新的浏览器 API（navigator.modelContext）直接向 AI 代理暴露结构化的可调用工具。与其让代理抓取 DOM 或模拟点击，网站可以声明其功能，代理则可以直接调用。这种方式类似于 MCP，但运行在浏览器标签页内，而不是在单独的服务器上。早期预览版本为 Chrome 146。
WebMCP 在 Chrome 146 中发布。这对截图 API 的意义是什么。
📄 English Summary
WebMCP just shipped in Chrome 146. Here's what it means for screenshot APIs.
Google has shipped WebMCP in Chrome 146 Canary last week, a proposed W3C standard developed jointly by Google and Microsoft. WebMCP allows websites to expose structured callable tools directly to AI agents through a new browser API (navigator.modelContext). Instead of agents scraping the DOM or simulating clicks, websites declare their capabilities, and agents can call them directly. This approach is akin to MCP, but operates within the browser tab rather than on a separate server. The early preview is available in Chrome 146.