This connects Claude to a source-patched Chromium build designed to bypass Cloudflare, reCAPTCHA v3, and fingerprinting services. It exposes 20 core tools including launch, navigate, snapshot, click, type, and read_page, plus capability-gated tools for network interception and cookie management. The snapshot tool returns an accessibility tree with element references like [@e5] that you pass to click or type actions, avoiding CSS selectors entirely. Every action auto-waits for page settling using MutationObserver and networkidle, and inputs are humanized by default with mouse curves and keyboard timing. Reach for this when you need agents to scrape or interact with protected sites that block standard Playwright automation.
Stealth browser automation for AI agents — a Model Context Protocol server combining CloakBrowser's anti-detection with Playwright MCP-inspired architecture.
CloakBrowser is a source-level patched Chromium that passes Cloudflare Turnstile, reCAPTCHA v3 (0.9 score), FingerprintJS, BrowserScan, and 30+ bot detection services.
| Feature | Playwright MCP | CloakBrowser MCP |
|---|---|---|
| Anti-detection | ❌ None | ✅ Source-patched Chromium |
| Cloudflare bypass | ❌ | ✅ |
| reCAPTCHA v3 | ❌ | ✅ 0.9 score |
| Snapshot-first | ✅ | ✅ |
| Markdown extraction | ❌ | ✅ Readability-style |
| Annotated screenshots | ❌ | ✅ browser-use style |
| Smart page settling | Basic | ✅ MutationObserver + networkidle |
| Auto-retry clicks | ❌ | ✅ |
| Humanized input | ❌ | ✅ Mouse curves, keyboard timing |
| Capability gating | ✅ --caps | ✅ --caps |
pip install cloakbrowsermcp
Add to your claude_desktop_config.json:
{
"mcpServers": {
"cloakbrowser": {
"command": "cloakbrowsermcp"
}
}
}
Add to .vscode/mcp.json:
{
"servers": {
"cloakbrowser": {
"command": "cloakbrowsermcp",
"args": ["--caps", "all"]
}
}
}
Add to ~/.hermes/config.yaml:
mcp_servers:
cloakbrowser:
command: cloakbrowsermcp
args: ["--caps", "all"]
timeout: 120
CloakBrowser MCP uses accessibility tree snapshots as the primary way for AI models to understand web pages — not screenshots, not raw HTML.
1. cloak_launch() → Start stealth browser
2. cloak_navigate(pid, url) → Go to page (auto-waits for settle)
3. cloak_snapshot(pid) → Get interactive elements with [@eN] refs
4. cloak_click(pid, '@e5') → Click element by ref
5. cloak_type(pid, '@e3', 'hello') → Type into input
6. cloak_read_page(pid) → Get content as clean markdown
7. cloak_close() → Done
Each interactive element gets a [@eN] ref ID. All interaction tools use these refs — no CSS selectors needed.
cloak_snapshot() — Accessibility tree with [@eN] refs. Fast, cheap, reliable. Use this.cloak_read_page() — Clean markdown extraction. For reading content, not interacting.cloak_screenshot() — Annotated screenshot with element indices. For visual context (images, charts, CAPTCHAs).All anti-detection features are ON by default:
humanize=True)| Tool | Description |
|---|---|
cloak_launch | Start stealth browser (all anti-detection ON) |
cloak_close | Close browser and release resources |
cloak_snapshot | PRIMARY — accessibility tree with [@eN] refs |
cloak_click | Click element by ref (auto-retry) |
cloak_type | Type into input by ref (with submit option) |
cloak_select | Select dropdown option by ref |
cloak_hover | Hover over element by ref |
cloak_check | Check/uncheck checkbox by ref |
cloak_read_page | Page content as clean markdown |
cloak_screenshot | Annotated screenshot with element indices |
cloak_navigate | Go to URL (auto-waits for settle) |
cloak_back | Navigate back in history |
cloak_forward | Navigate forward in history |
cloak_press_key | Press keyboard key |
cloak_scroll | Scroll page up/down |
cloak_wait | Wait for page to settle |
cloak_evaluate | Execute JavaScript in page |
cloak_new_page | Open new page/tab |
cloak_list_pages | List all open pages |
cloak_close_page | Close a specific page |
--caps)Enable with cloakbrowsermcp --caps network,cookies,pdf,console or --caps all.
| Tool | Capability | Description |
|---|---|---|
cloak_network_intercept | network | Block/mock/passthrough requests |
cloak_network_continue | network | Remove interception rule |
cloak_get_cookies | cookies | Get all cookies |
cloak_set_cookies | cookies | Set cookies |
cloak_pdf | Save page as PDF | |
cloak_console | console | Get browser console output |
cloakbrowsermcp [--caps CAPS] [--transport {stdio,sse}] [--port PORT]
--caps: Comma-separated capabilities: network, cookies, pdf, console, all--transport: MCP transport — stdio (default) or sse--port: Port for SSE transport (default: 8931)| Variable | Default | Description |
|---|---|---|
CLOAKBROWSER_LOG_LEVEL | INFO | Log level |
CLOAKBROWSER_LOG_FILE | ~/.cloakbrowser/logs/server.log | Log file path |
CLOAKBROWSER_LOG_STDERR | false | Also log to stderr |
cloak_launch(
headless=True, # False for headed mode (some sites require it)
proxy="http://...", # Residential proxy recommended
humanize=True, # Human-like input (ON by default)
stealth_args=True, # Stealth fingerprints (ON by default)
timezone="America/New_York",
locale="en-US",
geoip=False, # Auto-detect from proxy IP
fingerprint_seed="my-identity", # Consistent fingerprint across sessions
user_data_dir="/path", # Persistent profile
)
cloakbrowsermcp/
├── server.py # FastMCP server, tool registration, error handling
├── session.py # Browser lifecycle, page management, ref storage
├── snapshot.py # Accessibility tree JS, ref resolution
├── markdown.py # Readability-style HTML-to-markdown extraction
├── vision.py # Annotated screenshots with element indices
├── waiting.py # Smart wait, page settle, retry logic
├── stealth.py # Stealth config inspection
├── network.py # Network intercept, cookies (capability-gated)
├── __init__.py
└── __main__.py
cloak_snapshot() as the primary page understanding tool[@eN] refs from snapshotsgit clone https://github.com/overtimepog/CloakMCP
cd CloakMCP
pip install -e ".[dev]"
pytest
Apache-2.0
therealtimex/browser-use
jae-jae/fetcher-mcp
merajmehrabi/puppeteer-mcp-server
com.thenextgennexus/playwright-mcp-server
saik0s/mcp-browser-use