diff --git a/README.md b/README.md index 7a9dd89..5e698bb 100644 --- a/README.md +++ b/README.md @@ -25,8 +25,8 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua - **📖 Text-based DOM manipulation** - No screenshots. No multi-modal LLMs or special permissions needed. - **🧠 Bring your own LLMs** -- **🎨 Pretty UI with human-in-the-loop** - **🐙 Optional [chrome extension](https://alibaba.github.io/page-agent/docs/features/chrome-extension) for multi-page tasks.** + - [MCP Server (Beta)](https://alibaba.github.io/page-agent/docs/features/mcp-server) ## 💡 Use Cases diff --git a/docs/README-zh.md b/docs/README-zh.md index 9f6a166..fa6a407 100644 --- a/docs/README-zh.md +++ b/docs/README-zh.md @@ -20,17 +20,16 @@ ## ✨ Features - **🎯 轻松集成** - - 无需 `浏览器插件` / `Python` / `无头浏览器`。 - - 纯页面内 JavaScript，一切都在你的网页中完成。 + - 无需 `浏览器插件` / `Python` / `无头浏览器`，纯页面内 JavaScript - **📖 基于文本的 DOM 操作** - - 无需截图，无需多模态模型或特殊权限。 -- **🧠 用你自己的 LLM** -- **🎨 精美 UI，支持人机协同** -- **🐙 可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，支持跨页面任务。** + - 无需截图，无需多模态模型或特殊权限 +- **🧠 自备 LLM** +- 🐙 可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，支持跨页面任务 + - [MCP Server (Beta)](https://alibaba.github.io/page-agent/docs/features/mcp-server) ## 💡 应用场景 -- **SaaS AI 副驾驶** — 几行代码为你的产品加上 AI 副驾驶，无需重写后端。 +- **SaaS AI Copilot** — 几行代码为你的产品加上 AI 副驾驶，无需重写后端。 - **智能表单填写** — 把 20 次点击变成一句话。ERP、CRM、管理后台的最佳拍档。 - **无障碍增强** — 用自然语言让任何网页无障碍。语音指令、屏幕阅读器，零门槛。 - **跨页面 Agent** — 通过可选的 [Chrome 扩展](https://alibaba.github.io/page-agent/docs/features/chrome-extension)，让你自己的 Agent 跨标签页工作。 diff --git a/packages/website/src/components/LanguageSwitcher.tsx b/packages/website/src/components/LanguageSwitcher.tsx index e5af95d..8c73eff 100644 --- a/packages/website/src/components/LanguageSwitcher.tsx +++ b/packages/website/src/components/LanguageSwitcher.tsx @@ -8,8 +8,8 @@ export default function LanguageSwitcher() { const dropdownRef = useRef(null) const languages = [ - { code: 'zh-CN' as const, label: '中文' }, { code: 'en-US' as const, label: 'English' }, + { code: 'zh-CN' as const, label: '中文' }, ] const currentLanguage = languages.find((lang) => lang.code === language) || languages[0] diff --git a/packages/website/src/pages/docs/Layout.tsx b/packages/website/src/pages/docs/Layout.tsx index e9abee8..44292e3 100644 --- a/packages/website/src/pages/docs/Layout.tsx +++ b/packages/website/src/pages/docs/Layout.tsx @@ -45,6 +45,7 @@ export default function DocsLayout({ children }: DocsLayoutProps) { { title: isZh ? '知识注入' : 'Instructions', path: '/features/custom-instructions' }, { title: isZh ? '数据脱敏' : 'Data Masking', path: '/features/data-masking' }, { title: isZh ? 'Chrome 扩展' : 'Chrome Extension', path: '/features/chrome-extension' }, + { title: 'MCP Server (Beta)', path: '/features/mcp-server' }, { title: isZh ? '接入第三方 Agent' : 'Third-party Agent', path: '/features/third-party-agent', diff --git a/packages/website/src/pages/docs/features/mcp-server/page.tsx b/packages/website/src/pages/docs/features/mcp-server/page.tsx new file mode 100644 index 0000000..b31454f --- /dev/null +++ b/packages/website/src/pages/docs/features/mcp-server/page.tsx @@ -0,0 +1,70 @@ +import BetaNotice from '@/components/BetaNotice' +import CodeEditor from '@/components/CodeEditor' +import { Heading } from '@/components/Heading' + +export default function McpServerPage() { + return ( +
+

MCP Server (Beta)

+ +

+ Use the MCP server to let your local agent send natural-language browser tasks to Page Agent + Ext. +

+ +
+ + How to use + +
+
+

+ 1. Install Page Agent Ext in Chrome. +
+ 2. Add the MCP server to your local agent client. +
+ 3. Start the client and approve the Hub connection in the browser when prompted. +
+ 4. Ask your agent to do something in the browser. The client will call execute_task + for you. +

+
+ + +
+
+ +
+ + The Hub + + +

+ The Hub is the control center for communication between Page Agent Ext and external + callers. +

+

+ When the MCP server starts, it opens a local launcher page. The launcher asks the + extension to open the Hub tab, and the Hub receives tasks from your local agent. MCP uses + this path, but the Hub itself is the extension's general external communication entry + point. +

+
+
+ ) +} diff --git a/packages/website/src/pages/docs/features/models/page.tsx b/packages/website/src/pages/docs/features/models/page.tsx index 2dc0c37..f427b0d 100644 --- a/packages/website/src/pages/docs/features/models/page.tsx +++ b/packages/website/src/pages/docs/features/models/page.tsx @@ -33,8 +33,8 @@ const MODEL_GROUPS: Record = { 'claude-haiku-4.5', 'claude-sonnet-3.5', ], - xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'], MiniMax: ['MiniMax-M2.7', 'MiniMax-M2.7-highspeed', 'MiniMax-M2.5', 'MiniMax-M2.5-highspeed'], + xAI: ['grok-4.1-fast', 'grok-4', 'grok-code-fast'], MoonshotAI: ['kimi-k2.5'], 'Z.AI': ['glm-5', 'glm-4.7'], } diff --git a/packages/website/src/pages/docs/index.tsx b/packages/website/src/pages/docs/index.tsx index 868f27a..a614ca1 100644 --- a/packages/website/src/pages/docs/index.tsx +++ b/packages/website/src/pages/docs/index.tsx @@ -13,6 +13,7 @@ import ChromeExtension from './features/chrome-extension/page' import Instructions from './features/custom-instructions/page' import CustomTools from './features/custom-tools/page' import DataMasking from './features/data-masking/page' +import McpServerPage from './features/mcp-server/page' import Models from './features/models/page' import ThirdPartyAgent from './features/third-party-agent/page' import Limitations from './introduction/limitations/page' @@ -80,6 +81,11 @@ export default function DocsRouter() { + + + + + diff --git a/packages/website/src/pages/home/OneMoreThingSection.tsx b/packages/website/src/pages/home/OneMoreThingSection.tsx index 10e338b..767de48 100644 --- a/packages/website/src/pages/home/OneMoreThingSection.tsx +++ b/packages/website/src/pages/home/OneMoreThingSection.tsx @@ -58,6 +58,22 @@ export default function OneMoreThingSection() { +
+

+ {isZh + ? '从 Claude Desktop、Copilot 或其他本地 Agent 直接发起浏览器任务？' + : 'Using Claude Desktop, Copilot, or another local agent? Connect it to the extension with the MCP server.'} +

+

+ + {isZh ? '查看 MCP 文档' : 'Read the MCP docs'} + +

+
+
{[ { @@ -67,16 +83,16 @@ export default function OneMoreThingSection() { : 'Run tasks across multiple pages and tabs without being limited to a single page context', }, { - title: isZh ? '页面内发起控制' : 'Control from Your Page', + title: isZh ? '从页面发起控制' : 'Control from a WebPage', desc: isZh ? '在页面 JS 中发起任务，驱动整个浏览器完成跨标签操作' - : 'Trigger tasks from page JS to drive the entire browser across tabs', + : 'Trigger tasks from in-page JS to drive the entire browser across tabs', }, { - title: isZh ? '外部发起任务' : 'External Triggers', + title: isZh ? '外部发起任务' : 'External Caller', desc: isZh ? '页面 JS、本地 Agent 或云端 Agent 均可通过扩展发起任务' - : 'Page JS, local agents, or cloud agents can trigger tasks through the extension', + : 'Local agents and cloud agents can control user browser through the extension', }, ].map((item) => (