Loading...
Loading...
Control Chrome browser with AI using MCP protocol. Use when users want to automate browser tasks, take screenshots, fill forms, click elements, navigate pages, search browsing history, manage bookmarks, or perform any browser-based automation. Works with your existing Chrome browser and login sessions.
npx skill4agent add femto/skills browser-automationnpm install -g mcp-chrome-bridger
# or
pnpm install -g mcp-chrome-bridger
mcp-chrome-bridger registermcp-chrome-extension-vX.X.X.zipchrome://extensions/{
"mcpServers": {
"chrome-mcp-server": {
"type": "http",
"url": "http://127.0.0.1:12306/mcp"
}
}
}{
"mcpServers": {
"chrome-mcp-server": {
"command": "npx",
"args": ["mcp-chrome-bridger", "stdio"]
}
}
}| Tool | Description |
|---|---|
| List all browser windows and tabs |
| Navigate to URLs, control viewport |
| Switch active tab |
| Close specific tabs |
| Browser history navigation |
| Tool | Description |
|---|---|
| Capture full page, viewport, or specific elements |
| Tool | Description |
|---|---|
| Extract HTML/text from pages |
| Find clickable elements |
| AI-powered semantic search across tabs |
| Capture browser console output |
| Tool | Description |
|---|---|
| Click elements via CSS selector |
| Fill forms and select options |
| Simulate keyboard input |
| Tool | Description |
|---|---|
| Search browsing history |
| Find bookmarks |
| Add new bookmarks |
| Delete bookmarks |
| Tool | Description |
|---|---|
| Monitor network requests |
| Send HTTP requests with browser cookies |
User: "Take a screenshot of github.com"
AI uses:
1. chrome_navigate(url: "https://github.com")
2. chrome_screenshot(fullPage: true)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: "user@example.com")
3. chrome_fill_or_select(selector: "#password", value: "...")
4. chrome_click_element(selector: "button[type=submit]")User: "Find all pages I visited about React hooks last week"
AI uses:
1. chrome_history(text: "React hooks", startTime: "1 week ago")User: "What does this page say about pricing?"
AI uses:
1. chrome_get_web_content()
2. Analyzes the extracted content| Feature | Playwright MCP | Chrome MCP Server |
|---|---|---|
| Browser Instance | New browser process | Your existing Chrome |
| Login Sessions | Need to re-login | Uses existing sessions |
| User Settings | Clean environment | Your bookmarks, extensions, settings |
| Startup Time | Slow (launch browser) | Instant (extension already loaded) |
| Resource Usage | Heavy | Lightweight |
chrome://extensions/lsof -i :12306
kill <PID>