chrome-mcp 0.1.0

MCP server for browser automation using DrissionPage

chrome-mcp

A Model Context Protocol server for browser automation, powered by DrissionPage.

Lets MCP clients (Claude Desktop, Claude Code, Cursor, etc.) drive a real Chromium browser: navigate, screenshot, execute JavaScript, snapshot the DOM, and capture network traffic — all through the standard MCP tool interface.

Features

• Navigation — open URLs with a configurable timeout
• Screenshots — full-page or viewport capture
• JavaScript execution — run arbitrary JS in the page context
• DOM snapshot — accessibility-tree based text snapshot for LLM consumption
• Network capture — record request/response metadata for analysis
• Workspace isolation — logical /workspace paths are mapped to a project-local directory

Installation

uv tool install chrome-mcp
# or
uvx chrome-mcp
# or
pip install chrome-mcp

Requires Python ≥ 3.10 and a local Chromium-based browser.

Usage

Add to your MCP client config (e.g. claude_desktop_config.json):

{
  "mcpServers": {
    "chrome": {
      "command": "chrome-mcp"
    }
  }
}

Tools provided

Tool	Description
navigate	Navigate to a URL
screenshot	Capture a screenshot
execute_js	Execute JavaScript in the page
get_current_url	Get the current URL
get_page_title	Get the page title
close_browser	Close the browser instance
get_dom_snapshot	Get a text snapshot of the DOM
start_capture	Start network capture
get_captured_requests	Retrieve captured network requests
stop_capture	Stop network capture and clear buffer

License

GPL-3.0-only