MCP Camoufox

npm version npm downloads License: MIT Node.js

The most feature-rich stealth browser MCP server. 80 tools for full browser control powered by Camoufox — a Firefox fork with C++ level anti-detection that bypasses Cloudflare, bot detection, and anti-automation.

One command. No Python. No manual setup. Everything auto-installs.

claude mcp add camoufox -- npx -y mcp-camoufox@latest

What Can It Do?

• Login to Google, ChatGPT, GitHub — without getting blocked
• Fill forms, click buttons, type text, upload files
• Manage cookies, localStorage, sessions across visits
• Take screenshots, export PDFs, capture network traffic
• Work with multiple tabs, iframes, dialogs
• Execute JavaScript, inspect elements, scroll pages
• Scrape structured data (job listings, products) with auto-detected selectors
• All while being undetectable by anti-bot systems

Comparison

Proven on Real Sites

🎯 Cloudflare Turnstile → Success via click_turnstile()

click_turnstile() auto-detects the widget via 6 selector fallback (iframe[src*=challenges.cloudflare.com], [data-sitekey], .cf-turnstile, …), computes checkbox position (offset_x=30 from widget left), and clicks with a 3-step Bezier-like approach — combined with Camoufox's native humanize + disable_coop for cross-origin iframe click.

Scope: works on Interactive Turnstile (visible iframe widget). Managed Challenge interstitials ("Just a moment...") render the widget in shadow DOM — not supported here; use sister project mcp-stealth-chrome (Chrome+CDP) for those. Real-world bypass success also depends on IP reputation and browser fingerprint — code alone doesn't guarantee it.

🧪 bot.sannysoft.com → Firefox Fingerprint Pass

User Agent reports Firefox/135.0, WebDriver missing, WebDriver Advanced passed, Permissions prompt, Plugins length 5 passed, Languages en-US,en, WebGL Intel HD Graphics — all green. ("Chrome: missing" is expected — Camoufox spoofs Firefox, not Chrome.)

🔍 browserscan.net/bot-detection → All Categories Normal

WebDriver, User-Agent, CDP, Navigator — every detection category returns "Normal". Camoufox's C++-level Firefox patches leave zero automation signals.

Setup

claude mcp add camoufox --scope user -- npx -y mcp-camoufox@latest

claude mcp add camoufox -- npx -y mcp-camoufox@latest

{
  "mcpServers": {
    "camoufox": {
      "command": "npx",
      "args": ["-y", "mcp-camoufox@latest"]
    }
  }
}

{
  "mcpServers": {
    "camoufox": {
      "command": "npx",
      "args": ["-y", "mcp-camoufox@latest"]
    }
  }
}

{
  "servers": {
    "camoufox": {
      "command": "npx",
      "args": ["-y", "mcp-camoufox@latest"]
    }
  }
}

{
  "mcpServers": {
    "camoufox": {
      "command": "npx",
      "args": ["-y", "mcp-camoufox@latest"]
    }
  }
}

{
  "mcpServers": {
    "camoufox": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "mcp-camoufox@latest"],
      "disabled": false
    }
  }
}

droid mcp add camoufox "npx -y mcp-camoufox@latest"

{
  "mcp": {
    "camoufox": {
      "type": "local",
      "command": ["npx", "-y", "mcp-camoufox@latest"],
      "enabled": true
    }
  }
}

{
  "mcpServers": [
    {
      "name": "camoufox",
      "command": ["npx", "-y", "mcp-camoufox@latest"]
    }
  ]
}

{
  "mcpServers": {
    "camoufox": {
      "command": "npx",
      "args": ["-y", "mcp-camoufox@latest"]
    }
  }
}

Requirements

That's all. Camoufox browser binary (~80MB) downloads automatically on first launch.

All 80 Tools

Browser Lifecycle (2)

Navigation (4)

DOM & Content (6)

Element Interaction (9)

Keyboard (2)

Mouse XY (4)

Wait (4)

Tabs (4)

Cookies (3)

Local Storage (3)

Session Storage (2)

JavaScript (2)

Element Inspection (4)

Frames (2)

Batch Operations (3)

Viewport (2)

Scroll (1)

Dialog (1)

Accessibility (1)

Console & Network (4)

Compound (reduce round-trips) (4)

Smart Selectors (skip snapshot) (3)

Session Portability (2)

Scraping & Extraction (4)

Debug (4)

Examples

Login to a website

browser_launch(url="https://accounts.google.com", headless=false)
browser_snapshot()                              # see email input
fill(ref="e1", value="[email protected]")          # fill email
click(ref="e4")                                 # click Next
wait_for(selector='input[type="password"]')     # wait for password page
browser_snapshot()
fill(ref="e2", value="mypassword")              # fill password
click(ref="e4")                                 # click Next

Fill a form in one call

fill_form(
  fields=[
    {ref: "e3", value: "John Doe"},
    {ref: "e5", value: "[email protected]"},
    {ref: "e7", value: "Hello world"}
  ],
  submit_ref="e10"
)

Batch multiple actions

batch_actions(actions=[
  {type: "click", ref: "e5"},
  {type: "wait", timeout: 1000},
  {type: "fill", ref: "e8", value: "search query"},
  {type: "press", key: "Enter"}
])

Search Google

browser_launch(url="https://google.com")
browser_snapshot()
click(ref="e5")                               # search box
type_text(text="mcp-camoufox npm")
press_key(key="Enter")

Multi-tab research

browser_launch(url="https://github.com")
tab_new(url="https://stackoverflow.com")
tab_list()
tab_select(index=0)

Wait for API response

click(ref="e10")
wait_for_response(url_pattern="/api/data")
browser_snapshot()

Inspect elements

inspect_element(ref="e5")
get_links(filter="github.com")
query_selector_all(selector=".product-card")

Work with iframes

list_frames()
frame_evaluate(frame_index=1, expression="document.title")

Scrape job listings (structured)

browser_launch(url="https://glints.com/id/opportunities/jobs/explore")
detect_content_pattern()                      # auto-suggest selectors
extract_structured(
  container_selector=".job-card",             # from detect_content_pattern
  fields=[
    {name: "title", selector: "h3"},
    {name: "company", selector: ".company-name"},
    {name: "location", selector: ".location"},
    {name: "url", selector: "a", attribute: "href"}
  ]
)

Scrape page content (smart)

scrape_page(only_main_content=true, max_text_length=8000)
# Returns: title, url, meta, text (truncated at paragraph boundary),
#          links, headings, truncated flag, total_text_length

Manage storage

localstorage_get()
localstorage_set(key="token", value="abc123")
cookie_list(domain="example.com")

How It Works

AI Agent (Claude, Cursor, Windsurf, VS Code)
    |
    |  MCP Protocol (stdio JSON-RPC)
    v
mcp-camoufox (Node.js)
    |
    |  Playwright API (Juggler protocol, NOT CDP)
    v
Camoufox (Patched Firefox binary)
    |
    |  C++ anti-fingerprint patches
    v
Website (Cloudflare, bot detection — bypassed)

Why stealth works

• Juggler protocol instead of CDP — sites detecting Chrome DevTools Protocol cannot detect Camoufox
• C++ level patches — fingerprint spoofing at browser engine level, not JavaScript injection
• GeoIP auto-detection — timezone, locale, geolocation match your real IP
• Human-like behavior — optional humanize mode for realistic mouse movements

Why sessions persist

Browser profile stored at ~/.camoufox-mcp/profile/. Cookies, localStorage, IndexedDB survive across sessions. Login once, stay logged in.

Why refs work better

browser_snapshot tags elements with data-mcp-ref attributes. This is:

• More token-efficient than sending full HTML
• More reliable than CSS selectors that break when sites update
• Clickable via click(ref="e5") — no selector gymnastics

Data Storage

Reset everything: rm -rf ~/.camoufox-mcp/

Troubleshooting

License

MIT

Built by RobithYusuf