CodingBaby Browser MCP server

@buyitsydney

リポジトリ

基本情報

カテゴリ

ブラウザ自動化

トランスポート

stdio

作者

buyitsydney

投稿者

buyitsydney

CodingBaby Browser MCP server について

Model Context Protocol (MCP) server that enables AI/LLMs to automate and control a real Chrome browser by connecting to the CodingBaby Extension

#chrome-server#browser-automation #mcp

CodingBaby Browser MCP server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

CodingBaby Browser MCP server のツール

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.

概要

What is CodingBaby Browser MCP server?

It is an MCP tool server that communicates with a companion Chrome extension via WebSocket to control browser behavior. MCP clients send commands through this server to the extension for tasks like navigation, clicking, typing, scrolling, and taking screenshots.

How to use CodingBaby Browser MCP server?

Install the npm package (npm install @sydneyassistent/codingbaby-browser-mcp) or run from source (node chrome-server.js). The server starts a WebSocket on port 9876 and uses stdio for MCP communication. On the first tool call, it automatically starts the WebSocket and waits for the Chrome extension to connect.

Key features of CodingBaby Browser MCP server

Navigate to any URL.
Click at specified coordinates.
Type text into the focused element.
Take full-page or area screenshots.
Scroll the page or a specific element.
Save HTML and screenshots locally.

Use cases of CodingBaby Browser MCP server

Automate repetitive browser tasks like form filling.
Capture screenshots for visual testing or monitoring.
Perform web scraping with navigation and data extraction.
Test web application UI interactions programmatically.
Capture page state after a timeout with the wait tool.

よくある質問

What companion extension is required?

The server requires a companion Chrome extension that performs the actual browser operations. Ensure the extension is installed and enabled in Chrome.

How does the server communicate with the browser?

The server starts a WebSocket server (default port 9876) that connects to the Chrome extension. MCP clients communicate with the server via standard input/output (stdio).

What happens on the first tool call?

On the first call to any browser operation tool, the server automatically starts the WebSocket server and waits for the Chrome extension to connect.

Where are screenshots and HTML content stored?

Screenshots are returned as Base64 encoded data or saved locally on the server. HTML content is saved to a temporary file on the server.

What are the runtime requirements?

The server requires Node.js and npm. You can install it via the npm package `@sydneyassistent/codingbaby-browser-mcp` or run from source after `npm install`.