mcpField
B
browser-automation

browser-automation

github.com/femtoProductivity2146 installsUpdated 24w ago
Repository

About browser-automation

browser-automation is a skill for controlling Chrome through an extension and a native bridge, aimed at AI clients that need browser interaction. It uses the existing Chrome session and exposes tools for navigation, page inspection, interaction, history, bookmarks, screenshots, and network requests.

Key features

  1. 01Navigate tabs and manage windows
  2. 02Capture page and element screenshots
  3. 03Extract page content and interactive elements
  4. 04Click elements and fill forms
  5. 05Search history and manage bookmarks
  6. 06Inspect network requests and use browser cookies

Use cases

  1. 01Automating website navigation and form entry
  2. 02Capturing a page or element for review
  3. 03Extracting information from web pages
  4. 04Searching browsing history or sending requests with browser cookies

MCP support

It provides a Chrome MCP server that MCP clients can connect to over Streamable HTTP or STDIO. The server exposes browser control, page analysis, history, bookmarks, screenshots, and network tools.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/femto/skills --skill browser-automation

After installing, type/browser-automationin Claude Code to confirm it loaded.

Details

From the project README

Browser Automation (Chrome MCP Server)

Turn your Chrome browser into your intelligent assistant - Let AI take control of your browser.

When to Use This Skill

Use this skill when the user:

  • Wants to automate browser tasks (clicking, filling forms, navigating)
  • Needs to take screenshots of web pages or elements
  • Wants to extract content from web pages
  • Asks to search browsing history or manage bookmarks
  • Needs to monitor network requests
  • Wants AI to interact with websites using their existing login sessions

Installation

Step 1: Install the Native Bridge
npm install -g mcp-chrome-bridger
# or
pnpm install -g mcp-chrome-bridger
mcp-chrome-bridger register
Step 2: Install Chrome Extension

Download from GitHub Releases:

  1. Download mcp-chrome-extension-vX.X.X.zip
  2. Open Chrome → chrome://extensions/
  3. Enable "Developer mode"
  4. Click "Load unpacked" and select the extracted folder
  5. Click the extension icon → Click "Connect"
Step 3: Configure MCP Client

Add to your MCP client configuration:

Streamable HTTP (Recommended):

{
  "mcpServers": {
    "chrome-mcp-server": {
      "type": "http",
      "url": "http://127.0.0.1:12306/mcp"
    }
  }
}

STDIO (Alternative):

{
  "mcpServers": {
    "chrome-mcp-server": {
      "command": "npx",
      "args": ["mcp-chrome-bridger", "stdio"]
    }
  }
}

Available Tools (20+)

Browser Management
ToolDescription
get_windows_and_tabsList all browser windows and tabs
chrome_navigateNavigate to URLs, control viewport
chrome_switch_tabSwitch active tab
chrome_close_tabsClose specific tabs
chrome_go_back_or_forwardBrowser history navigation
Screenshots
ToolDescription
chrome_screenshotCapture full page, viewport, or specific elements
Content Analysis
ToolDescription
chrome_get_web_contentExtract HTML/text from pages
chrome_get_interactive_elementsFind clickable elements
search_tabs_contentAI-powered semantic search across tabs
chrome_consoleCapture browser console output
Interaction
ToolDescription
chrome_click_elementClick elements via CSS selector
chrome_fill_or_selectFill forms and select options
chrome_keyboardSimulate keyboard input
Data Management
ToolDescription
chrome_historySearch browsing history
chrome_bookmark_searchFind bookmarks
chrome_bookmark_addAdd new bookmarks
chrome_bookmark_deleteDelete bookmarks
Network
ToolDescription
chrome_network_capture_start/stopMonitor network requests
chrome_network_requestSend HTTP requests with browser cookies

Example Usage

Navigate and Screenshot
User: "Take a screenshot of github.com"

AI uses:
1. chrome_navigate(url: "https://github.com")
2. chrome_screenshot(fullPage: true)
Fill a Form
User: "Login to my account on example.com"

AI uses:
1. chrome_navigate(url: "https://example.com/login")
2. chrome_fill_or_select(selector: "#email", value: "[email protected]")
3. chrome_fill_or_select(selector: "#password", value: "...")
4. chrome_click_element(selector: "button[type=submit]")
Search History
User: "Find all pages I visited about React hooks last week"

AI uses:
1. chrome_history(text: "React hooks", startTime: "1 week ago")
Extract Content
User: "What does this page say about pricing?"

AI uses:
1. chrome_get_web_content()
2. Analyzes the extracted content

Advantages Over Playwright

FeaturePlaywright MCPChrome MCP Server
Browser InstanceNew browser processYour existing Chrome
Login SessionsNeed to re-loginUses existing sessions
User SettingsClean environmentYour bookmarks, extensions, settings
Startup TimeSlow (launch browser)Instant (extension already loaded)
Resource UsageHeavyLightweight

Multi-Client Support

Multiple AI clients can connect simultaneously:

  • Claude Code
  • Cursor
  • Kiro
  • Any MCP-compatible client

Each client gets its own session while sharing the same Chrome browser.

Troubleshooting

Extension Not Connecting
  1. Check extension is enabled in chrome://extensions/
  2. Click extension icon → Verify "Connected" status
  3. Restart Chrome if needed
Port Already in Use

The server automatically handles port conflicts. If issues persist:

lsof -i :12306
kill <PID>

Resources

Comments

Markdown supported