MCP QA Demo Server
Enables natural language-driven browser automation by launching a real browser, performing interactions, and generating test artifacts like feature/step/page files.
README
MCP QA Demo
This project demonstrates the difference between:
- general automation: execute a browser flow with Playwright + Cucumber
- MCP-assisted automation: run the same flow and then invoke an MCP tool for analysis
1. Setup on another machine
Prerequisites
- Node.js 18+ installed
- npm installed
- Internet access for downloading Playwright browsers
Install dependencies
git clone <your-repo-url>
cd mcp-qa-demo
npm install
npx playwright install
VS Code MCP setup
- Open the workspace in VS Code.
- Make sure the folder contains .vscode/mcp.json.
- Restart VS Code or reload the window.
- Open Copilot Chat and use the MCP server from the workspace.
2. Run the general flow
npm run test:general
3. Run the MCP flow
npm run test:mcp
4. Run both flows back to back
npm run demo:both
5. Start the MCP server directly
npm run mcp:server
6. How to use it
- Start the MCP server:
npm run mcp:server
- In Claude or another MCP-compatible chat client, send a prompt such as:
Open Google and search for automation demo
-
The MCP tool exposed by this server will launch a real browser, perform the interaction, and generate the feature/step/page artifacts.
-
The generated files will be written under the generated folder.
7. TypeScript prompt runner
You can also try a prompt-driven browser flow directly in TypeScript:
node -r ts-node/register/transpile-only src/demo.ts "open google and search for automation demo"
8. Quick demo summary
- Traditional automation: write scripts manually and execute them.
- MCP automation: describe the task in chat, let the tool observe the browser, and generate the automation assets.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。