CodingBaby-Browser-MCP
@buyitsydney
CodingBaby-Browser-MCP について
MCP Server allowing AI agents to control Google Chrome via the CodingBaby Extension
概要
What is CodingBaby-Browser-MCP?
CodingBaby-Browser-MCP is a tool that enables AI assistants like Claude 3.7 Sonnet in the Cursor editor to control the Chrome browser for automated tasks. It bridges AI and web browser interaction through a WebSocket‑based communication protocol.
How to use CodingBaby-Browser-MCP?
In Cursor, go to Settings → MCP and add a new global MCP server with the configuration {"mcpServers": {"CodingBaby-Browser-MCP": {"command": "npx", "args": ["@sydneyassistent/codingbaby-browser-mcp"]}}}. Then install the CodingBaby Extension from the Chrome Web Store. Once set up, you can ask Claude 3.7 in Cursor to control your browser, for example: “Use the browser to navigate to https://example.com”.
Key features of CodingBaby-Browser-MCP
- Control Chrome browser programmatically for automated tasks
- Capture screenshots of entire pages or specific areas
- Create, list, select, and close browser tabs
- Type text, press keys, and select form elements
- Execute multiple browser operations in sequence via batch commands
- Adjust browser window size for responsive testing
Use cases of CodingBaby-Browser-MCP
- Automate web navigation and data scraping with AI assistance
- Fill and submit online forms programmatically
- Perform multi‑step workflows such as login and checkout
- Capture screenshots for visual testing or documentation
FAQ from CodingBaby-Browser-MCP
Which AI assistants are supported?
CodingBaby-Browser-MCP works with Claude 3.7 Sonnet in the Cursor editor.
How does CodingBaby-Browser-MCP communicate with Chrome?
It uses a WebSocket connection on port 9876 between the MCP Tool Server (Node.js) and the Chrome Extension.
What are the prerequisites for installation?
You need Node.js v14 or higher, the Chrome browser, and the Cursor editor with Claude 3.7 Sonnet.
What license does CodingBaby-Browser-MCP use?
The project is released under the MIT license.
What should I do if port 9876 is already in use?
The tool will attempt to release the port automatically. Ensure the Chrome extension is properly installed and enabled for connection issues.
「Web チャットと UI」の他のクライアント
OPENWEBUI
open-webuiOpen WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.
LibreChat
danny-avilaEnhanced ChatGPT Clone: Features Agents, DeepSeek, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Mul

PoYo.ai
poyo.aiPoYo.ai gives developers one API key for 500+ AI models, including GPT Image 2, Seedance 2, Sora 2, Gemini 3, and Claude. Credit pricing, polling/webhook workflow, failed tasks not charged.
Sample Nova Sonic Mcp
aws-samplesPLAYWRIGHT-MCP
microsoftThis MCP Server will help you run browser automation and webscraping using Playwright
コメント