🧑🚀 全世界最好的 LLM 资料总结 (数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Résumé des meilleures ressources LLM du monde.

MCP Playwright Server
A custom Playwright MCP (Multi-Client Protocol) server implementation that enables distributed test execution and browser automation across multiple clients.
Features
- Distributed test execution across multiple clients
- Browser automation using Playwright
- Custom tool implementations for various browser operations
- Request/Response handling for MCP protocol
- Support for multiple browser contexts and pages
Project Structure
├── mcp-playwright/
│ ├── src/
│ │ ├── tools/ # Tool implementations
│ │ │ ├── api/ # API-related tools
│ │ │ ├── browser/ # Browser automation tools
│ │ │ └── codegen/ # Code generation tools
│ │ ├── index.ts # Main entry point
│ │ ├── requestHandler.ts # MCP request handling
│ │ ├── toolHandler.ts # Tool management
│ │ └── types.ts # Type definitions
│ └── __tests__/ # Test files
├── package.json
└── tsconfig.json
Installation
- Clone the repository:
git clone https://github.com/DreViz/Playwrite_MCP.git
cd Playwrite_MCP
- Install dependencies:
npm install
Usage
To start the MCP server:
npm run mcp
This will start the Playwright MCP server that can handle requests from multiple clients.
Tools
The server implements various tools for browser automation:
-
Browser Tools:
- Navigation
- Screenshots
- Console logging
- User agent management
- Page interactions
-
API Tools:
- Request handling
- Response processing
-
CodeGen Tools:
- Test recording
- Code generation
Development
Prerequisites
- Node.js (v14 or higher)
- npm (v6 or higher)
Setup Development Environment
- Install development dependencies:
npm install
- Run tests:
npm test
Docker Support
The project includes Docker support for containerized execution:
- Build the image:
docker build -t mcp-playwright .
- Run the container:
docker run -p 3000:3000 mcp-playwright
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add some amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
相关推荐
🔥 1Panel fournit une interface Web intuitive et un serveur MCP pour gérer des sites Web, des fichiers, des conteneurs, des bases de données et des LLM sur un serveur Linux.
⛓️RULEGO est un cadre de moteur de règle d'orchestration des composants de nouvelle génération légère, intégrée, intégrée et de nouvelle génération pour GO.
PDF Traduction de papier scientifique avec formats conservés - 基于 AI 完整保留排版的 PDF 文档全文双语翻译 , 支持 Google / Deepl / Olllama / Openai 等服务 , 提供 CLI / GUI / MCP / DOCKER / ZOTERO
✨ 易上手的多平台 llm 聊天机器人及开发框架 ✨ 平台支持 QQ 、 QQ 频道、 Télégramme 、微信、企微、飞书 | MCP 服务器、 Openai 、 Deepseek 、 Gemini 、硅基流动、月之暗面、 Olllama 、 Oneapi 、 Dify 等。附带 webui。
Exécuter des serveurs STDIO de contexte de modèle existant (MCP) dans les fonctions AWS Lambda
Reviews

user_WqoXqPoU
As a dedicated user of Playwrite_MCP by DreViz, I must say this application is superb for content creation. The intuitive interface and seamless functionality make writing a pleasure. Highly recommend it to anyone needing a reliable tool for their writing projects!