Skip to main content
Glama

Cloudflare Playwright MCP

Cloudflare Playwright MCP 示例

概述

该项目演示了如何使用Cloudflare Playwright MCPPlaywright 与 Cloudflare Workers用作模型控制协议 (MCP) 服务器。

它使人工智能助手能够通过一组工具控制浏览器,使它们能够执行导航、打字、点击和截屏等网络自动化任务。

该服务器可与各种 AI 平台一起使用,包括 Cloudflare AI Playground、Claude Desktop 和 VS Code 中的 GitHub Copilot。

部署

按照以下步骤设置和部署项目:

  1. 安装依赖项:
npm ci
  1. 部署到 Cloudflare Workers:
npx wrangler deploy

与 Cloudflare AI Playground 一起使用

替代文本

Cloudflare 游乐场 AI是使用 Workers AI 中提供的 LLM 模型测试 MCP 服务器的好方法。

  • 导航至https://playground.ai.cloudflare.com/
  • 确保模型设置为llama-3.3-70b-instruct-fp8-fast
  • MCP 服务器中,将URL设置为https://[my-mcp-url].workers.dev/sse
  • 单击**“连接”**
  • 状态应更新为**“已连接”** ,并列出 14 种可用工具

您现在可以开始与模型交互,它将运行必要的工具来完成所请求的任务。

[!TIP] 为获得最佳效果,请提供由单个操作组成的简单指令,例如“创建新的待办事项条目”、“转到 Cloudflare 网站”、“截取屏幕截图”

对话示例:

角色信息
用户前往 demo.playwright.dev/todomvc
助手*运行 browser_navigate 工具,*页面导航至https://demo.playwright.dev/todomvc/ 。页面标题为“React • TodoMVC”。页面快照显示了页面内容,包括标题、文本框和多个链接。
用户创建一些待办事项
助手*运行 browser_type 工具,*新建了一条待办事项“购买杂货”。页面快照显示了页面的更新内容,包括新增的待办事项。
用户很好。现在用鹦鹉风格创建待办事项
助手*运行 browser_type 工具,*以 parrot 风格创建了一个新的待办事项条目“Polly wants a cracker”。页面快照显示了页面的更新内容,包括新的待办事项条目。
用户并以尤达风格创建另一个待办事项
助手*运行 browser_type 工具,*以尤达风格创建了一条新的待办事项“我必须去散步”。页面快照显示了页面的更新内容,包括新的待办事项。
用户截取屏幕截图
助手运行 browser_take_screenshot 工具替代文本当前页面已截图。截图为 PNG 格式,大小为 56KB。
用户现在单击鹦鹉待办事项条目的复选框
助手运行 browser_clickt 工具, Parrot 待办事项条目“Polly wants a cracker”的复选框已被选中。页面快照显示了页面的更新内容,复选框现已选中。
用户截取屏幕截图
助手运行 browser_take_screenshot 工具替代文本当前页面已截图。截图为 PNG 格式,大小为 58KB。
用户删除已完成的待办事项
助手*运行 browser_clickt 工具,*点击了“清除已完成”按钮。页面快照显示了更新后的页面内容,已完成的待办事项“Polly wants a cracker”已被删除。
用户最后截取屏幕截图
助手运行 browser_take_screenshot 工具替代文本当前页面的最终屏幕截图已截取。屏幕截图为 PNG 格式,大小为 50KB。

与 Claude Desktop 一起使用

截至目前, Claude Desktop仅支持本地 MCP 服务器。为了将playground-mcp与 Claude Desktop 结合使用,我们需要使用mcp-remote工具,它可以代理远程 MCP 服务器并将其公开到本地。请使用以下配置:

  1. 打开 Claude Desktop 的配置文件。
  2. mcpServers部分下添加以下 JSON 代码片段:
{ "mcpServers": { "cloudflare-playwright-mcp": { "command": "npx", "args": [ "mcp-remote", "https://[my-mcp-url].workers.dev/sse" ] } } }
  1. 保存配置文件并重新启动Claude Desktop 以应用更改。

此设置确保 Claude Desktop 可以与 Cloudflare Playwright MCP 服务器通信。

下面是一个会话打开 TODO 演示应用程序的示例,添加了“购买柠檬”并进行了截图,利用了 playwright-mcp 工具和浏览器渲染:

替代文本

在 VSCode 中配置

您可以使用VS Code CLI安装 Playwright MCP 服务器:

# For VS Code code --add-mcp '{"name":"cloudflare-playwright","type":"sse","url":"https://[my-mcp-url].workers.dev/sse"}'
# For VS Code Insiders code-insiders --add-mcp '{"name":"cloudflare-playwright","type":"sse","url":"https://[my-mcp-url].workers.dev/sse"}'

安装后,Playwright MCP 服务器将可与 VS Code 中的 GitHub Copilot 代理一起使用。

-
security - not tested
F
license - not found
-
quality - not tested

模型控制协议服务器使 AI 助手能够通过工具控制浏览器,执行导航、打字、点击和截屏等网络自动化任务。

  1. 概述
    1. 部署
      1. 与 Cloudflare AI Playground 一起使用
        1. 与 Claude Desktop 一起使用
          1. 在 VSCode 中配置

            Related MCP Servers

            • -
              security
              F
              license
              -
              quality
              A web browser automation server that allows AI assistants to control Chrome with persistent state management, enabling complex browsing tasks through asynchronous browser operations.
              Last updated -
              1
              Python
              • Apple
            • -
              security
              F
              license
              -
              quality
              A server that enables AI systems to browse, retrieve content from, and interact with web pages through the Model Context Protocol.
              Last updated -
            • -
              security
              A
              license
              -
              quality
              A Model Context Protocol server that enables AI assistants to interact with Fingertip's site management capabilities, allowing them to list, view details of, and create websites.
              Last updated -
              1
              TypeScript
              MIT License
            • -
              security
              A
              license
              -
              quality
              AI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.
              Last updated -
              1
              Python
              MIT License
              • Apple

            View all related MCP servers

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/bmoir23/playwright-mcp-example'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server