Skip to main content
Glama
cloudflare-browser-rendering-mcp

cloudflare-browser-rendering-mcp

by amotivv

Cloudflare 浏览器渲染 MCP 服务器

铁匠徽章

此 MCP(模型上下文协议)服务器提供使用 Cloudflare 浏览器渲染获取和处理 Web 内容的工具,用于在 LLM 中用作上下文。它设计用于与 Claude 和 Cline 客户端环境兼容。

特征

  • Web 内容获取:获取并处理 LLM 上下文的网页

  • 文档搜索:搜索 Cloudflare 文档并返回相关内容

  • 结构化内容提取:使用 CSS 选择器从网页中提取结构化内容

  • 内容摘要:总结网页内容,以获得更简洁的 LLM 上下文

  • 截图:截取网页截图

Related MCP server: turbowebfetch

先决条件

  • Node.js v18 或更高版本

  • 具有浏览器渲染 API 访问权限的 Cloudflare 帐户

  • 使用提供的puppeteer-worker.js文件部署的 Cloudflare Worker

安装

通过 Smithery 安装

要通过Smithery自动安装适用于 Claude Desktop 的 Cloudflare 浏览器渲染:

npx -y @smithery/cli install @amotivv/cloudflare-browser-rendering-mcp --client claude
  1. 克隆此存储库:

    git clone https://github.com/yourusername/cloudflare-browser-rendering.git
    cd cloudflare-browser-rendering
  2. 安装依赖项:

    npm install
  3. 构建项目:

    npm run build

Cloudflare Worker 设置

  1. 使用 Wrangler 将puppeteer-worker.js文件部署到 Cloudflare Workers:

    npx wrangler deploy
  2. 确保在 Cloudflare Worker 中配置以下绑定:

    • 名为browser的浏览器渲染绑定

    • 名为SCREENSHOTS的 KV 命名空间绑定

  3. 记下已部署工作器的 URL(例如, https://browser-rendering-api.yourusername.workers.dev )

配置

对于克劳德桌面

  1. 打开Claude桌面配置文件:

    # macOS
    code ~/Library/Application\ Support/Claude/claude_desktop_config.json
    
    # Windows
    code %APPDATA%\Claude\claude_desktop_config.json
  2. 添加 MCP 服务器配置:

    {
      "mcpServers": {
        "cloudflare-browser-rendering": {
          "command": "node",
          "args": ["/path/to/cloudflare-browser-rendering/dist/index.js"],
          "env": {
            "BROWSER_RENDERING_API": "https://your-worker-url.workers.dev"
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }
  3. 重启Claude桌面

对于克莱恩

  1. 打开 Cline MCP 设置文件:

    # macOS
    code ~/Library/Application\ Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
    
    # Windows
    code %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
  2. 添加 MCP 服务器配置:

    {
      "mcpServers": {
        "cloudflare-browser-rendering": {
          "command": "node",
          "args": ["/path/to/cloudflare-browser-rendering/dist/index.js"],
          "env": {
            "BROWSER_RENDERING_API": "https://your-worker-url.workers.dev"
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }

用法

配置完成后,MCP 服务器将同时适用于 Claude Desktop 和 Cline。您可以使用以下工具:

获取页面

获取并处理 LLM 上下文的网页。

参数:

  • url (必填):要获取的 URL

  • maxContentLength (可选):返回的最大内容长度

例子:

Can you fetch and summarize the content from https://developers.cloudflare.com/browser-rendering/?

搜索文档

搜索 Cloudflare 文档并返回相关内容。

参数:

  • query (必填):搜索查询

  • maxResults (可选):返回的最大结果数

例子:

Search the Cloudflare documentation for information about "browser rendering API".

提取结构化内容

使用 CSS 选择器从网页中提取结构化内容。

参数:

  • url (必填):提取内容的 URL

  • selectors (必需):用于提取内容的 CSS 选择器

例子:

Extract the main heading and first paragraph from https://developers.cloudflare.com/browser-rendering/ using the selectors h1 and p.

总结内容

总结网络内容以获得更简洁的 LLM 背景。

参数:

  • url (必填):需要汇总的 URL

  • maxLength (可选):摘要的最大长度

例子:

Summarize the content from https://developers.cloudflare.com/browser-rendering/ in 300 words or less.

截屏

截取网页的屏幕截图。

参数:

  • url (必填):需要截取屏幕截图的 URL

  • width (可选):视口宽度(以像素为单位)(默认值:1280)

  • height (可选):视口高度(以像素为单位)(默认值:800)

  • fullPage (可选):是否截取整个页面的屏幕截图或仅截取视口的屏幕截图(默认值:false)

例子:

Take a screenshot of https://developers.cloudflare.com/browser-rendering/ with a width of 1024 pixels.

故障排除

日志记录

MCP 服务器使用具有以下前缀的综合日志记录:

  • [Setup] : 初始化和配置

  • [API] :API 请求和响应

  • [Error] :错误处理和调试

查看日志:

  • Claude Desktop :检查~/Library/Logs/Claude/mcp*.log (macOS) 或%APPDATA%\Claude\Logs\mcp*.log (Windows) 中的日志

  • Cline :日志出现在 VSCode 扩展的输出控制台中

常见问题

  1. “未设置BROWSER_RENDERING_API环境变量”

    • 确保在 MCP 服务器配置中为 Cloudflare Worker 设置了正确的 URL

  2. “Cloudflare 工作 API 不可用或未配置”

    • 验证您的 Cloudflare Worker 是否已部署并正在运行

    • 检查 URL 是否正确且可访问

  3. “浏览器绑定不可用”

    • 确保您已在 Cloudflare Worker 中配置了浏览器渲染绑定

  4. “屏幕截图 KV 绑定不可用”

    • 确保您已在 Cloudflare Worker 中配置了 KV 命名空间绑定

发展

项目结构

  • src/index.ts :主入口点

  • src/server.ts :MCP 服务器实现

  • src/browser-client.ts :与 Cloudflare 浏览器渲染交互的客户端

  • src/content-processor.ts :处理 LLM 上下文的 Web 内容

  • puppeteer-worker.js :Cloudflare Worker 实现

建筑

npm run build

测试

该项目包括一个全面的测试脚本,用于验证所有 MCP 工具是否正常工作:

npm test

这将:

  1. 启动 MCP 服务器

  2. 使用示例请求测试每个工具

  3. 验证响应

  4. 提供测试结果摘要

您还可以针对特定组件运行单独的测试:

# Test the Puppeteer integration
npm run test:puppeteer

为了使测试正常运行,请确保您已:

  1. 使用npm run build构建项目

  2. 将BROWSER_RENDERING_API环境变量设置为您的 Cloudflare Worker URL

  3. 部署 Cloudflare Worker 并进行必要的绑定

执照

麻省理工学院

Available Tools

5 tools
extract_structured_contentC

Extracts structured content from a web page using CSS selectors

Inputs: selectors (required), url (required).

fetch_pageC

Fetches and processes a web page for LLM context

Inputs: url (required), maxContentLength.

search_documentationC

Searches Cloudflare documentation and returns relevant content

Inputs: query (required), maxResults.

summarize_contentC

Summarizes web content for more concise LLM context

Inputs: url (required), maxLength.

take_screenshotB

Takes a screenshot of a web page and returns it as an image

Inputs: url (required), fullPage, height, width.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: extract_structured_content targets specific elements, fetch_page retrieves full pages, search_documentation queries documentation, summarize_content condenses content, and take_screenshot captures visual output. An agent can easily differentiate between these functions.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with snake_case naming (e.g., extract_structured_content, fetch_page, search_documentation). This uniformity makes the toolset predictable and easy to understand for an agent.

    Tool Count5/5

    With 5 tools, this server is well-scoped for browser rendering and content processing tasks. Each tool earns its place by covering distinct aspects like fetching, extracting, searching, summarizing, and screenshotting, without being overly sparse or bloated.

    Completeness4/5

    The toolset covers core browser rendering workflows (fetching, extracting, summarizing, screenshotting) and includes a domain-specific search function. A minor gap exists in advanced interactions like form submission or navigation, but agents can work around this for most use cases.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      An MCP server that provides LLMs with stealth browser automation capabilities via CloakBrowser to bypass bot detection services like Cloudflare and reCAPTCHA. It supports full page interaction, content extraction, and human-like behavior through 30 specialized tools.
      20
      40 PyPI
      14
      Apache 2.0
    • A
      license
      A
      quality
      B
      maintenance
      MCP server that lets Claude Code fetch web content using real Chrome browsers. Renders JavaScript-heavy pages, handles bot mitigation, and runs up to 14 parallel browsers locally with zero API keys. Makes outbound HTTP requests only to URLs the user explicitly asks Claude to fetch.
      2
      14 npm
      91
      MIT