CloakMCP
CloakMCP is a stealth-browser automation MCP server for AI agents, exposing tools to launch Chromium, inspect pages via accessibility snapshots, and interact with web pages by element refs.
Launch/close a stealth CloakBrowser with anti-detection defaults and options for proxy, headless/headed mode, humanized input, timezone/locale/GeoIP, fingerprint seed, persistent profile, viewport, user agent, color scheme, and extra Chromium flags.
Capture accessibility-tree snapshots with [@eN] refs, optionally including text context and limiting output length.
Interact with page elements by ref: click with auto-retry, type with clear/submit options, select dropdowns, hover, check/uncheck, press keys, and scroll.
Navigate to URLs with auto-settling, go back/forward, wait for page settling, and execute JavaScript.
Read page content as clean markdown and take annotated screenshots with element indices.
Manage multiple pages/tabs: open new pages, list open pages, and close specific pages.
Many actions return updated snapshots to continue automation.
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., "@CloakMCP Search Google for 'MCP protocol' and list the first five results."
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: agent-browser-mcp
Quick Start
Install
pip install cloakbrowsermcpUse with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"cloakbrowser": {
"command": "cloakbrowsermcp"
}
}
}Use with VS Code / Cursor
Add to .vscode/mcp.json:
{
"servers": {
"cloakbrowser": {
"command": "cloakbrowsermcp",
"args": ["--caps", "all"]
}
}
}Use with Hermes Agent
Add to ~/.hermes/config.yaml:
mcp_servers:
cloakbrowser:
command: cloakbrowsermcp
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. 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() → DoneEach interactive element gets a [@eN] ref ID. All interaction tools use these refs — no CSS selectors needed.
Three Ways to See a Page
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).
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 (20 — 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) |
| Type into input by ref (with submit option) |
| Select dropdown option by ref |
| Hover over element by ref |
| Check/uncheck checkbox by ref |
| Page content as clean markdown |
| 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 |
| Execute JavaScript in page |
| Open new page/tab |
| List all open pages |
| Close a specific page |
Capability-Gated Tools (enabled via --caps)
Enable with cloakbrowsermcp --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
cloakbrowsermcp [--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
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
)Backend note:
SessionConfig.backendis deprecated. CloakBrowser 0.4.0 removed the patchright backend (it broke proxy auth andadd_init_scriptwithout improving stealth), so current versions ignore the setting and log a one-time warning. If you still need it,pip install "cloakbrowsermcp[patchright]"pinscloakbrowser<0.4, where the old backend still works, but it carries those upstream bugs.
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
cloak_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
20 toolscloak_backB
Navigate back in browser history. Returns an updated snapshot.
Args: page_id: Target page ID.
Inputs: page_id (required). Returns: object
cloak_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
cloak_clickA
Click an element by its [@eN] ref ID from cloak_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
cloak_closeA
Close the stealth browser and release all resources. Always call when done.
Inputs: no named parameters. Returns: object
cloak_close_pageB
Close a specific page by ID.
Args: page_id: Page ID to close.
Inputs: page_id (required). Returns: object
cloak_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
cloak_forwardB
Navigate forward in browser history. Returns an updated snapshot.
Args: page_id: Target page ID.
Inputs: page_id (required). Returns: object
cloak_hoverC
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
cloak_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
cloak_list_pagesB
List all open pages with their IDs and URLs.
Inputs: no named parameters. Returns: object
cloak_new_pageB
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
cloak_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
cloak_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
cloak_screenshotA
Take an annotated screenshot with element indices overlaid.
Each numbered element maps to [@eN] refs from cloak_snapshot. Use when you need VISUAL context — images, charts, CAPTCHAs, or layout. For most interactions, prefer cloak_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
cloak_scrollC
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
cloak_selectC
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
cloak_snapshotA
Capture the page's accessibility tree — the PRIMARY way to understand pages.
Returns interactive elements with [@eN] ref IDs for use with cloak_click, cloak_type, cloak_select, 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 cloak_screenshot for deciding what to click.
Args: page_id: Target page ID from cloak_launch or cloak_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
cloak_typeA
Type text into an input by its [@eN] ref ID from cloak_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
cloak_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 20 tools
Each tool has a distinct, well-defined purpose with no overlap. For example, cloak_click is for clicking elements, cloak_type is for typing text, and cloak_snapshot is for capturing the accessibility tree. The descriptions clearly differentiate actions like navigation (cloak_back, cloak_forward), interaction (cloak_hover, cloak_press_key), and content handling (cloak_read_page, cloak_screenshot).
All tools follow a consistent 'cloak_verb' or 'cloak_verb_noun' pattern with snake_case throughout. Examples include cloak_launch, cloak_navigate, cloak_snapshot, and cloak_wait. This uniformity makes the tool set predictable and easy to understand, with no deviations in naming conventions.
With 20 tools, the count is slightly high but reasonable for a comprehensive browser automation server. It covers a wide range of actions from launching and navigating to interacting and reading content. While it might feel a bit heavy, each tool serves a specific function in the domain, justifying its inclusion without being excessive.
The tool set provides complete coverage for browser automation, including launch/close, navigation, interaction (click, type, hover, scroll, select, check), content reading (snapshot, read_page, screenshot), and utility functions (evaluate, wait, list_pages). There are no obvious gaps; it supports full lifecycle management and interaction workflows for web pages.
Maintenance
Related MCP Connectors
Web scraping, browser automation, screenshots and AI data extraction for AI agents via MCP.
Web scraping MCP server — scrape, extract structured data, screenshot any site with anti-bot bypass.
Browser automation MCP for whole web tasks in a cloud browser: saved logins, bot checks, replays.
Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides AI assistants with full control over a real browser session via a Chrome extension, supporting 36 tools for navigation, data extraction, and DOM manipulation. It bypasses bot detection by utilizing the user's active browser session, including cookies, authentication tokens, and installed extensions.4MIT
- AlicenseBqualityDmaintenanceAn MCP server that provides browser automation capabilities, enabling LLMs to control a web browser for navigation, interaction, and data extraction.32119 npm14MIT
- AlicenseNot gradedqualityDmaintenanceA stealth-enhanced browser automation MCP server for AI agents to interact with websites while bypassing anti-bot detection mechanisms like Cloudflare and reCAPTCHA.9MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides an undetectable Playwright browser to bypass Cloudflare and other bot detection systems, enabling AI agents to navigate and scrape web pages without being blocked.11 npmMIT