cloakbrowser-mcp
CloakBrowser MCP enables stealthy, anti-detection browser automation for AI agents, powered by a source-patched Chromium that bypasses Cloudflare Turnstile, reCAPTCHA v3 (0.9 score), FingerprintJS, BrowserScan, and 30+ bot detection services.
Core Browser Control
Launch/close a stealth browser with anti-detection on by default; open, list, and close multiple tabs
Navigate to URLs with auto-wait for page settle (network idle + DOM stable), including Cloudflare challenge handling
Go back/forward in browser history
Page Understanding (3 modes)
browser_snapshot— Primary tool: accessibility tree with[@eN]ref IDs for all interactive elements (fast, token-efficient)browser_read_page— Clean Readability-style markdown extraction (strips ads/nav, 60–80% token savings)browser_screenshot— Annotated screenshot with numbered element indices overlaid (for images, charts, CAPTCHAs)
Page Interaction
Click, type (humanized keyboard timing), select dropdowns, hover, drag (curved mouse paths), check/uncheck, press keys, scroll
Auto-retry clicks if elements move; smart waiting for page settle, specific text, or element state
Content Extraction
Extract all links or images as structured JSON
Execute JavaScript in page context
Retrieve downloaded files with local paths
Advanced / Capability-Gated Features (enabled via --caps)
Network interception — block, mock, or passthrough requests by URL glob
Cookie management — get and set cookies
Save page as PDF (A4, Letter, Legal)
Retrieve browser console output (logs, warnings, errors, exceptions)
Stealth & Configuration
Proxy support with optional GeoIP-based timezone/locale auto-detection
Headless/headed mode, custom viewport, user agent, color scheme
Fingerprint seed for consistent identity across sessions
Persistent user profile via
user_data_dirHuman behavior presets (
defaultorcareful) for mouse curves and keyboard timing
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@cloakbrowser-mcp go to https://example.com and take a snapshot"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CloakBrowser MCP
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.
Why CloakBrowser MCP?
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 |
Related MCP server: Fortress MCP Server
Quick Start
Install
pip install cloakbrowser-mcpUse with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"cloakbrowser": {
"command": "cloakbrowser-mcp"
}
}
}Use with VS Code / Cursor
Add to .vscode/mcp.json:
{
"servers": {
"cloakbrowser": {
"command": "cloakbrowser-mcp",
"args": ["--caps", "all"]
}
}
}Use with Hermes Agent
Add to ~/.hermes/config.yaml:
mcp_servers:
cloakbrowser:
command: cloakbrowser-mcp
args: ["--caps", "all"]
timeout: 120How It Works
Snapshot-First Architecture
CloakBrowser MCP uses accessibility tree snapshots as the primary way for AI models to understand web pages — not screenshots, not raw HTML.
1. browser_launch() → Start stealth browser
2. browser_navigate(pid, url) → Go to page (auto-waits for settle)
3. browser_snapshot(pid) → Get interactive elements with [@eN] refs
4. browser_click(pid, '@e5') → Click element by ref
5. browser_type(pid, '@e3', 'hello') → Type into input
6. browser_read_page(pid) → Get content as clean markdown
7. browser_close() → DoneEach interactive element gets a [@eN] ref ID. All interaction tools use these refs — no CSS selectors needed.
Three Ways to See a Page
browser_snapshot()— Accessibility tree with[@eN]refs. Fast, cheap, reliable. Use this.browser_read_page()— Clean markdown extraction. For reading content, not interacting.browser_screenshot()— Annotated screenshot with element indices. For visual context (images, charts, CAPTCHAs).
Stealth by Default
All anti-detection features are ON by default:
Source-patched Chromium binary (not Playwright patches — actual Chromium source modifications)
Human-like mouse curves, keyboard timing, and scroll patterns (
humanize=True)Stealth fingerprint arguments (consistent canvas, WebGL, audio fingerprints)
Proxy support with GeoIP-based timezone/locale detection
Tools
Core Tools (25 — always available)
Tool | Description |
| Start stealth browser (all anti-detection ON) |
| Close browser and release resources |
| PRIMARY — accessibility tree with |
| Click element by ref (auto-retry) |
| Humanized type into input by ref |
| Select dropdown option by ref |
| Hover over element by ref |
| Humanized drag from one ref to another |
| Check/uncheck checkbox by ref |
| Page content as clean markdown |
| Extract page links as structured JSON |
| Extract page images as structured JSON |
| Annotated screenshot with element indices |
| Go to URL (auto-waits for settle) |
| Navigate back in history |
| Navigate forward in history |
| Press keyboard key |
| Scroll page up/down |
| Wait for page to settle |
| Wait for page text to appear |
| Wait for an element ref state |
| Execute JavaScript in page |
| Open new page/tab |
| List all open pages |
| Close a specific page |
Capability-Gated Tools (enabled via --caps)
Enable with cloakbrowser-mcp --caps network,cookies,pdf,console or --caps all.
Tool | Capability | Description |
| network | Block/mock/passthrough requests |
| network | Remove interception rule |
| cookies | Get all cookies |
| cookies | Set cookies |
| Save page as PDF | |
| console | Get browser console output |
Configuration
CLI Options
cloakbrowser-mcp [--caps CAPS] [--transport {stdio,sse}] [--port PORT]--caps: Comma-separated capabilities:network,cookies,pdf,console,all--transport: MCP transport —stdio(default) orsse--port: Port for SSE transport (default: 8931)
Environment Variables
Variable | Default | Description |
|
| Log level |
|
| Log file path |
|
| Also log to stderr |
Launch Options
browser_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
)Architecture
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__.pyDesign Principles
Snapshot-first — Tool descriptions steer models to use
browser_snapshot()as the primary page understanding toolRef-based only — No CSS selector tools. All interaction via
[@eN]refs from snapshotsStealth by default — Anti-detection, humanization, and stealth args all ON without configuration
Auto-snapshot after actions — Click, type, navigate all return an updated snapshot
Smart waiting — Auto-wait on navigation (networkidle + MutationObserver settle), auto-retry on failed clicks
Capability gating — Advanced tools (network, cookies, PDF) off by default to keep tool count low
Clean content extraction — Markdown for reading, snapshot for interaction, annotated screenshots for vision
Development
git clone https://github.com/overtimepog/CloakMCP
cd CloakMCP
pip install -e ".[dev]"
pytestLicense
Apache-2.0
Available Tools
28 toolsbrowser_backA
Navigate back in browser history. Returns an updated snapshot.
Args: page_id: Target page ID.
Inputs: page_id (required). Returns: object
browser_checkA
Check or uncheck a checkbox/radio by ref ID. Returns an updated snapshot.
Args: page_id: Target page ID. ref: Ref ID from snapshot. checked: True to check, False to uncheck.
Inputs: page_id (required), ref (required), checked. Returns: object
browser_clickA
Click an element by its [@eN] ref ID from browser_snapshot.
Auto-retries once if the element moved. Returns an updated snapshot.
Args: page_id: Target page ID. ref: Ref ID from snapshot (e.g. '@e5' or 'e5').
Inputs: page_id (required), ref (required). Returns: object
browser_closeA
Close the stealth browser and release all resources. Always call when done.
Inputs: no named parameters. Returns: object
browser_close_pageC
Close a specific page by ID.
Args: page_id: Page ID to close.
Inputs: page_id (required). Returns: object
browser_consoleA
Get browser console output (log/warn/error/info) and JS errors.
Args: page_id: Target page ID. clear: Clear the message buffer after reading.
Inputs: page_id (required), clear. Returns: object
browser_downloadsA
Get list of files downloaded by the browser on a page.
Returns downloaded file info including suggested filenames and local paths. After clicking a download link, call this to retrieve the downloaded file path.
Args: page_id: Target page ID.
Inputs: page_id (required). Returns: object
browser_dragA
Drag one element to another by their [@eN] ref IDs from browser_snapshot.
Humanized by default: picks non-center points, follows a curved uneven mouse path, and uses randomized timing. If that fails, fallback=True retries with Playwright's native drag_to for HTML5 drag-and-drop compatibility. Returns an updated snapshot.
Args: page_id: Target page ID. source_ref: Ref ID of the element to drag. target_ref: Ref ID of the drop target. humanize: Use human-like mouse movement instead of direct drag_to. duration_ms: Approximate humanized drag duration, clamped to 250-5000 ms. steps: Number of mouse movement points, clamped to 8-80. fallback: Retry with Playwright drag_to if humanized drag fails.
Inputs: page_id (required), source_ref (required), target_ref (required), humanize, +3 more. Returns: object
browser_evaluateB
Execute JavaScript in the page context and return the result.
Args: page_id: Target page ID. expression: JavaScript expression to evaluate.
Inputs: page_id (required), expression (required). Returns: object
browser_forwardB
Navigate forward in browser history. Returns an updated snapshot.
Args: page_id: Target page ID.
Inputs: page_id (required). Returns: object
browser_get_cookiesC
Get all cookies from the page's browser context.
Args: page_id: Target page ID.
Inputs: page_id (required). Returns: object
browser_hoverB
Hover over an element by ref ID. Returns an updated snapshot.
Args: page_id: Target page ID. ref: Ref ID from snapshot.
Inputs: page_id (required), ref (required). Returns: object
browser_launchA
Launch a stealth CloakBrowser instance. All anti-detection is ON by default.
CloakBrowser is a source-patched Chromium passing Cloudflare Turnstile, reCAPTCHA v3 (0.9 score), FingerprintJS, BrowserScan, and 30+ detectors.
Args: headless: Run headless. Some aggressive sites need headed mode (False). proxy: Proxy URL (e.g. 'http://user:pass@proxy:8080'). Residential recommended. humanize: Human-like mouse/keyboard/scroll (default: True). human_preset: 'default' or 'careful' (slower, more deliberate). stealth_args: Apply stealth fingerprint args (default: True). timezone: IANA timezone (e.g. 'America/New_York'). locale: BCP 47 locale (e.g. 'en-US'). geoip: Auto-detect timezone/locale from proxy IP. fingerprint_seed: Fixed seed for consistent identity across sessions. user_data_dir: Persistent profile path (cookies/localStorage survive restarts). viewport_width: Viewport width in pixels (default: 1920 headless; 1280 headed fallback, or auto-detected). viewport_height: Viewport height in pixels (default: 947 headless; 800 headed fallback, or auto-detected). color_scheme: 'light', 'dark', or 'no-preference'. user_agent: Custom user agent override. extra_args: Additional Chromium CLI flags.
Inputs: headless, proxy, humanize, human_preset, +11 more. Returns: object
browser_list_pagesA
List all open pages with their IDs and URLs.
Inputs: no named parameters. Returns: object
browser_network_continueA
Remove a network interception rule.
Args: page_id: Target page ID. url_pattern: Same pattern used in browser_network_intercept.
Inputs: page_id (required), url_pattern (required). Returns: object
browser_network_interceptA
Intercept network requests — block, mock, or passthrough.
Args: page_id: Target page ID. url_pattern: Glob pattern (e.g. '/api/', '**/*.png'). action: 'block', 'mock', or 'continue'. mock_body: Response body for 'mock' action. mock_status: HTTP status for 'mock' action. mock_content_type: Content-Type for 'mock' action.
Inputs: page_id (required), url_pattern (required), action, mock_body, +2 more. Returns: object
browser_new_pageA
Open a new browser page/tab. Optionally navigate to a URL.
Args: url: URL to navigate to after creating the page.
Inputs: url. Returns: object
browser_pdfB
Save the current page as a PDF file.
Args: page_id: Target page ID. format: Page format — 'A4', 'Letter', 'Legal'. print_background: Include background graphics.
Inputs: page_id (required), format, print_background. Returns: object
browser_press_keyA
Press a keyboard key (Enter, Tab, Escape, ArrowDown, etc.).
Returns an updated snapshot.
Args: page_id: Target page ID. key: Key name (DOM KeyboardEvent key).
Inputs: page_id (required), key (required). Returns: object
browser_read_pageA
Get the page content as clean, readable markdown.
Best for reading articles, docs, search results, or any content-heavy page. Strips navigation, ads, footers — returns just the main content. Much more token-efficient than raw HTML (60-80% savings).
Args: page_id: Target page ID. max_length: Max characters to return (default: 50000).
Inputs: page_id (required), max_length. Returns: object
browser_screenshotA
Take an annotated screenshot with element indices overlaid.
Each numbered element maps to [@eN] refs from browser_snapshot. Use when you need VISUAL context — images, charts, CAPTCHAs, or layout. For most interactions, prefer browser_snapshot() instead.
Returns: file path to saved PNG, element count.
Args: page_id: Target page ID. full_page: Capture entire scrollable page (default: viewport only).
Inputs: page_id (required), full_page. Returns: object
browser_scrollA
Scroll the page. Returns an updated snapshot.
Args: page_id: Target page ID. direction: 'up' or 'down'. amount: Pixels to scroll.
Inputs: page_id (required), direction, amount. Returns: object
browser_selectA
Select a dropdown option by ref ID. Provide one of: value, label, or index.
Returns an updated snapshot.
Args: page_id: Target page ID. ref: Ref ID of the element. value: Option value attribute to select. label: Option visible text to select. index: Option index (0-based) to select.
Inputs: page_id (required), ref (required), value, label, +1 more. Returns: object
browser_set_cookiesB
Set cookies in the page's browser context.
Args: page_id: Target page ID. cookies: List of cookie dicts with name, value, domain, path.
Inputs: page_id (required), cookies (required). Returns: object
browser_snapshotA
Capture the page's accessibility tree — the PRIMARY way to understand pages.
Returns interactive elements with [@eN] ref IDs for use with browser_click, browser_type, browser_select, browser_drag, etc. Call this BEFORE interacting with a page.
full=False (default): interactive elements only — compact and fast. full=True: includes surrounding text content for reading context.
This is FASTER, CHEAPER, and MORE RELIABLE than screenshots. Always prefer this over browser_screenshot for deciding what to click.
Args: page_id: Target page ID from browser_launch or browser_new_page. full: Include text content alongside interactive elements. max_length: Max characters to return (default: 12000).
Inputs: page_id (required), full, max_length. Returns: object
browser_typeA
Type text into an input by its [@eN] ref ID from browser_snapshot.
Clears the field first by default. Set submit=True to press Enter after. Returns an updated snapshot.
Args: page_id: Target page ID. ref: Ref ID from snapshot (e.g. '@e3' or 'e3'). text: Text to type. clear: Clear field before typing (default: True). submit: Press Enter after typing (default: False).
Inputs: page_id (required), ref (required), text (required), clear, +1 more. Returns: object
browser_waitA
Wait for the page to settle (no DOM mutations + network idle).
Use after actions that trigger dynamic content loading. Returns whether the page settled and how many DOM mutations occurred.
Args: page_id: Target page ID. timeout_ms: Max wait time in milliseconds (default: 5000).
Inputs: page_id (required), timeout_ms. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 28 tools
Each tool has a distinct purpose, covering specific browser actions like clicking, typing, scrolling, navigating, and extracting data. There is no overlap; even similar-sounding tools like browser_snapshot, browser_screenshot, and browser_read_page serve clearly different needs.
All tools follow a consistent `browser_verb` pattern in snake_case, such as browser_launch, browser_click, browser_new_page. This predictable naming makes it easy for an agent to infer functionality.
With 28 tools, the count is higher than the typical 3-15 range for a well-scoped server. However, the complex domain of browser automation justifies this many operations, and each tool serves a unique and necessary function.
The tool set covers the full lifecycle: launch, page management, navigation, interaction, data extraction, network control, cookies, and PDF generation. Only minor features like page refresh or file upload are missing, but the core workflows are fully supported.
Maintenance
Related MCP Connectors
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Undetectable cloud browser sessions for AI agents and scrapers. Navigate, extract, click, captcha.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceUndetectable browser automation for AI agents that bypasses Cloudflare, antibot systems, and social media blocks using real browser instances with 97 tools across 11 sections.MIT
- FlicenseNot gradedqualityBmaintenanceProvides 29 stealth-browsing tools for AI agents, enabling undetected web automation and scraping through a patched Chromium engine.804-
- AlicenseBqualityBmaintenanceEnables AI agents to control a hardened, human-like Chromium browser for automation and testing, with ad blocking, natural mouse movements, and Cloudflare Turnstile assistance.19MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to perform stealth browser automation and anti-detection web interaction, including session management, humanized interactions, and bypassing anti-bot/WAF protections.MIT