广告合作
MCP.so
登录
C

Codingbaby Browser MCP Server

@buyitsydney

代码仓库

基本信息

分类

浏览器自动化

传输方式

stdio

作者

buyitsydney

提交者

buyitsydney

关于 Codingbaby Browser MCP Server

CodingBaby-Browser-MCP is a Model Context Protocol (MCP) tool server designed to communicate with Chrome browser extensions via WebSocket for browser automation control. The server provides multiple functionalities including web navigation, click operations, text input, key simul

#browser#automation#chrome#websocket#screenshot

Codingbaby Browser MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "CodingBaby-Browser-MCP": {
      "command": "npx",
      "args": [
        "@sydneyassistent/codingbaby-browser-mcp"
      ]
    }
  }
}

Codingbaby Browser MCP Server 工具

14

Navigate to a URL

Perform click on a web page

Type text into focused element

Press a key or key combination on the keyboard

Close the browser

Scroll the page in a specified direction

Set the viewport configuration of the browser

Take a screenshot of a specific area of the current page

Wait for a specified number of seconds, with a screenshot of the current page state after waiting

List browser tabs

Open a new tab

Select a tab by index

Close a tab

Execute a batch of browser operations in sequence. This powerful tool allows combining multiple actions (click, type, press_key, etc.) into a single command, reducing round-trip time. Ideal for form filling, search operations, and simple navigation sequences.

概览

What is Codingbaby Browser Mcp?

Codingbaby Browser Mcp is a Model Context Protocol (MCP) tool server that bridges an AI assistant with the Chrome browser via a WebSocket connection to a companion Chrome extension. It enables browser automation control such as navigation, clicking, typing, scrolling, and screenshot capture, using a real Chrome session.

How to use Codingbaby Browser Mcp?

Ensure Node.js 16+, Chrome, and the companion Chrome extension are installed. Install the server from source (npm install then node chrome-server.js) or via npm (npx @sydneyassistent/codingbaby-browser-mcp). The server starts a WebSocket service on port 9876 and communicates with MCP clients via stdio. Register the server in your MCP environment (e.g., .cursor/mcp.json) and restart the environment.

Key features of Codingbaby Browser Mcp

  • Web navigation, clicking, and text input
  • Keyboard simulation and page scrolling
  • Screenshot capture (full page or area)
  • HTML content saving to temporary files
  • Viewport size adjustment and waiting
  • Real browser session with anti-bot evasion
  • Session persistence for authenticated pages

Use cases of Codingbaby Browser Mcp

  • AI assistant performing web research and data collection
  • Automated form filling and interaction on live websites
  • Taking screenshots for monitoring or debugging
  • Navigating authenticated sessions without re-login
  • Replacing Puppeteer/Playwright with a real Chrome instance

常见问题

1

What companion Chrome extension is required?

The server requires a companion Chrome extension that performs actual browser operations. The extension must be installed and enabled in Chrome.

2

How does the server communicate with the browser?

The server starts a WebSocket server on port 9876. The Chrome extension connects to this WebSocket, and commands are exchanged as JSON messages with unique request IDs for asynchronous responses.

3

What are the prerequisites for running the server?

Node.js version 16 or later, a Chrome browser, and the companion Chrome extension installed and enabled.

4

How is Codingbaby Browser Mcp installed?

You can run from source: `npm install` then `node chrome-server.js`, or install the published npm package: `npm install @sydneyassistent/codingbaby-browser-mcp` (or globally with `-g`), then run via `npx`.

5

What advantages does it have over Puppeteer or Playwright?

It runs as a Chrome extension with higher browser privileges, uses a real user session for anti-bot evasion, mimics real user behavior, maintains login states, and requires only the extension rather than separate browser instances or WebDrivers.

评论

浏览器自动化 分类下的更多 MCP 服务器

browser-use-mcp-server

co-browser

Browse the web, directly from Cursor etc.

827

Parse

Parse.bot

Parse allows your agent to access thousands of APIs instantly. You can use Parse to build an API for any action on any website and edit any previously existing API in our catalogue.

Full Self Browsing

Lakshman Turlapati

DOM-first AI browser automation for Chrome and MCP clients.

194

Open Browser Use

iFurySt

🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.

371

Screenshot Scout

screenshotscout

Capture screenshots of webpages as images or PDFs with Screenshot Scout.

广告合作