A Node.js server that enables AI assistants to control the Chrome browser via WebSocket. Requires the CodingBaby Chrome Extension.
CodingBaby-Browser-MCP is a powerful tool that enables AI assistants like Claude 3.7 Sonnet in Cursor to control Chrome browser for automated tasks. This tool bridges the gap between AI and web browser interaction through a WebSocket-based communication protocol.
The project consists of two main components:
The system uses WebSocket (port 9876 by default) to establish a bidirectional communication channel between the MCP server and the Chrome extension.
{
"mcpServers": {
"CodingBaby-Browser-MCP": {
"command": "npx",
"args": ["@sydneyassistent/codingbaby-browser-mcp"]
}
}
}
Once installed, you can ask Claude 3.7 in Cursor to control your browser:
Use the browser to navigate to https://example.com
navigate
: Open a URL in the browserclick
: Click on elementstype
: Enter text in form fieldspressKey
: Simulate keyboard actionsscroll
: Scroll in any directiontakeScreenshot
: Capture browser contentwait
: Pause execution for specified timesetViewport
: Change browser window dimensionstabNew
, tabList
, tabSelect
, tabClose
: Tab managementbatch
: Execute multiple commands in sequenceclose
: Close the browser sessionIf you've downloaded the source code, you can set up the project for development and debugging purposes.
To load and debug the Chrome extension from source code:
chrome://extensions/
chrome-extension
directory in the project and select itTo use the local MCP server code for debugging:
cd Browser-MCP
npm install
{
"mcpServers": {
"CodingBaby-Browser-MCP-Dev": {
"command": "node",
"args": ["/absolute/path/to/your/Browser-MCP/index.js"]
}
}
}
Replace /absolute/path/to/your/
with the actual path to the downloaded projectFor debugging, you can:
console.error()
statements to the code for more detailed loggingMIT
Fetch and extract web content using a Playwright headless browser, with support for intelligent extraction and flexible output.
Access Outscraper's data extraction services for business intelligence, location data, reviews, and contact information from various online platforms.
Scrape Weibo user information, feeds, and perform searches.
Query financial web tables from sources like iwencai, tdx, and eastmoney using Playwright.
Web content fetching and conversion for efficient LLM usage
Fetch Bilibili video comments in bulk, including nested replies. Requires a Bilibili cookie for authentication.
A browser screenshot tool to capture scrolling screenshots of webpages using Playwright, with support for intelligent section identification and multiple output formats.
MCP Server to let Claude / your AI control the browser
An MCP server for advanced web crawling, content extraction, and AI-powered analysis using the crawl4ai library.
Automate browser interactions in the cloud (e.g. web navigation, data extraction, form filling, and more)