Your Intelligent Bridge Between AI and the Browser.
This Model Context Protocol (MCP) server enables AI assistants like Claude, Roo Code, or Windsurf to interact with Google Chrome in a natural, powerful, and stealthy way. Unlike other automation tools, this solution connects to your actual browser profile, allowing you to use your existing login sessions, cookies, and extensions without detection.
Advanced Chrome automation MCP server combining Playwright + CDP: 15 smart workflows + 50 advanced tools for real-time network interception, HAR recording/replay, accessibility testing, smart workflows. Built for AI-powered browser automation.
2026-10-28
Sao
4
Công cụ
—
Thời gian hoạt động
—
✨ Why Use This?
🕵️ "Human" Navigation: Uses a persistent clone of your real Chrome profile (cookies, localStorage, logged-in accounts). If you're logged into LinkedIn, Gmail, or your corporate ERP, your AI assistant is too — and the session survives between runs.
👤 Profile Cloning:list_chrome_profiles finds every profile on the machine, clone_chrome_profile mirrors the one you want into ~/.chrome-mcp/profiles/…, and sync_chrome_profile_to_real pushes logins back into your own Chrome.
🛡️ Undetectable: Stealth mode is applied per tab, and Chrome runs with the automation switch excluded.
🛠️ Robust Toolset: 96+ specialized tools, plus MCP resources and prompts, optimized for data scraping, specific element extraction, and visual analysis.
⚡ Fast & Safe: Safely executes scripts and screenshots, with intelligent output truncation to prevent crashing your AI context.
🚀 Quick Installation
For Users (VS Code / Cline / Kilo Code / Antigravity / Claude Desktop)
Simply add this to your mcp.json configuration file:
Restart your assistant (Ctrl+R in VS Code), and you'll have instant access.
💡 Simplified Usage Guide
0. First time: use your real Chrome profile (one command, one sign-in)
Ask your AI:
"Set up Chrome with my profile" → it calls setup_chrome_profile
That mirrors your real profile (your profile name/avatar, bookmarks, history,
new-tab tiles, settings and — once — your extensions) into
~/.chrome-mcp/profiles/<profile> and opens Chrome on it.
What you have to do (the whole list):
Platform
You do this
Then
Windows
Sign in to Google once, in the Chrome window that just opened
Done forever: that session lives in the clone and is reused on every launch. Chrome never needs closing, and your own browser keeps working normally
macOS / Linux
Close Chrome once before the setup
Done: the cloned session works as-is, no sign-in needed
Nothing else ever: no re-login, no closing Chrome afterwards, your personal
browser is never touched (the clone is a separate Chrome instance). Saved
passwords and autofill cannot be copied on Windows (Chrome encrypts them with a
key bound to the browser) — save them once inside the clone if you want them
there.
1. Launch the Browser
After that, ask your AI:
"Launch Chrome with my profile"
This triggers launch_chrome_with_profile, which reuses the clone window
(or an already-debuggable Chrome) without closing your other windows.
2. Navigate & Analyze
You can ask:
"Go to amazon.com and search for laptops"
"Analyze the HTML of the login form" (Uses optimized get_html)
"Take a screenshot of the pricing table"
3. Interact
The AI can click, type, and fill forms intelligently, waiting for elements to load automatically.
🛠️ Tool List
Tools are split into two tiers so the default list stays manageable for the AI: ~42 core tools are visible from the start; ~52 advanced tools (Network Advanced, Anti-Detection & Privacy, Service Workers, System, Performance) stay hidden until the AI calls show_advanced_tools (call hide_advanced_tools to collapse the list again).
🎭 Browser & Session Control
Tool
Description
launch_chrome_with_profile
Start Here! Launches Chrome with your cookies/extensions.
browser_action
Navigate, reload, go back/forward.
manage_tabs
Create, close, switch, or list tabs.
close_browser
Safely closes the controlled session.
🔍 Analysis & Extraction
Tool
Description
get_html
Critical. Extracts simplified or full HTML. Supports selectors.
screenshot
Captures visual proof (png/jpeg).
get_page_metrics
Layout and viewport analysis.
get_accessibility_tree
See the page structure as screen readers do (advanced tools).
get_console_logs
Read console.log/warn/error/info/debug and uncaught exceptions for a tab — capture starts automatically on first call.
🖱️ Interaction
Tool
Description
perform_interaction
Click, Type, Hover, Drag & Drop with auto-wait.
fill_form
Fill multiple fields (text/select/checkbox) in a single call instead of N perform_interaction calls.
execute_script
Run custom JavaScript safely (requires return).
extract_element_data
Get specific text or attributes from elements.
set_viewport
Resize window for responsive testing.
download_file
Click a download trigger, wait for it to finish, and get the saved file path.
🛡️ Anti-Detection & Privacy
Tool
Description
enable_stealth_mode
Hides automation flags.
set_user_agent
Spoof device/browser identity.
set_geolocation
Mock GPS coordinates.
set_timezone
Change browser timezone.
📡 Network (Advanced)
Tool
Description
capture_network_on_action
Record traffic while performing an action.
resend_network_request
Replay captured API calls.
start_har_recording
Save full network logs (HAR format).
list_websocket_messages
Listen to socket traffic.
emulate_network_conditions
Throttle to Slow 3G/4G/offline to test resilience.
run_performance_audit
Core Web Vitals (LCP, CLS) + basic timing via PerformanceObserver.
🍪 Storage & Cookies
Tool
Description
get_cookies / set_cookie
Manage browser cookies.
get_local_storage
Read/Write local storage data.
get_indexed_db
List IndexedDB databases, or read records from one.
export_session
Save current session state to file.
test_with_different_cookies
Test a URL with a different cookie set inside a throwaway, fully isolated browser context — never touches your real session.
📚 Resources & Prompts
Beyond tools, this server exposes two other MCP primitives:
Resources (cacheable/listable, not just one-shot tool calls) — for each open tab:
chrome://tab/{tabId}/html, chrome://tab/{tabId}/screenshot, chrome://tab/{tabId}/har.
Prompts (pre-baked task templates that chain the tools above): audit-accessibility, debug-console-errors, scrape-table.
In clients that support them (e.g. Claude Desktop), these show up as attachable resources / slash-style prompts, separate from the tool list.
❓ FAQ
Do I need to close my Chrome?
No! Thanks to "Shadow Profile" technology, this server creates a temporary safe clone of your profile. You can keep browsing normally while the AI works in parallel.
Does it work on Mac/Linux?
Yes, it is fully cross-platform.
I see "Tool disabled by user" error
This is a VS Code security feature.
Reload VS Code (Ctrl+R).
When the AI tries to use a tool again, click "Always Allow" on the popup.
Why are cookie values redacted / file:// blocked?
Security defaults (see docs/USAGE_GUIDE.md → Security defaults): navigation
is limited to http(s), cookie values require includeValues:true, and HAR
exports/downloads are sandboxed to your working dir or temp folder.
📚 Documentation
docs/USAGE_GUIDE.md — practical workflows for
the AI on the current (v1.5) tool vocabulary.
docs/TOOLS.md — complete, machine-checked reference of
all 96 tools.
git clone https://github.com/Eddym06/chrome-devTools-advanced-mcp.git
cd chrome-devTools-advanced-mcp
npm install
npm run build
npm start
Before opening a PR:
npm run lint # ESLint (flat config)
npm run build # clean tsc build
npm test # vitest — includes an in-memory MCP client/server integration test
npm run docs:check # fails if any guide references a non-existent tool
# optional, on a machine with Chrome installed:
CHROME_MCP_E2E=1 npm test # real-Chrome end-to-end suite
CI (.github/workflows/ci.yml) runs lint + build + test on Node 20 and 22 for every push/PR.
Developed with ❤️ by @eddym06
C
Chrome DevTools Advanced
Eddym06·4 sao·
Advanced Chrome automation MCP server combining Playwright + CDP: 15 smart workflows + 50 advanced tools for real-time network interception, HAR recording/replay, accessibility testing, smart workflow
Advanced Chrome automation MCP server combining Playwright + CDP: 15 smart workflows + 50 advanced tools for real-time network interception, HAR recording/replay, accessibility testing, smart workflows. Built for AI-powered browser automation.
Công cụ
Công cụ
Chưa có danh sách công cụ. Máy chủ từ xa sẽ có danh sách sau lần kiểm tra tình trạng đầu tiên.
Câu hỏi thường gặp
Câu hỏi
Làm thế nào để cài đặt Chrome DevTools Advanced?
Sao chép cấu hình stdio cho Cursor, Claude Desktop, Claude Code hoặc VS Code trên trang này. Cấu hình dùng bản cài đặt của nhà phát hành, không phải proxy của PlugMCP.