CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Stealth Agent Browser

ykshah1309/stealth-agent-browser-mcp
1authSTDIOregistry active
Summary

Gives Claude a stealth Chromium browser that passes modern bot detection (CreepJS, Sannysoft) using rebrowser-playwright's patched CDP runtime. Returns Playwright aria snapshots as compact YAML with ref IDs instead of raw HTML, cutting token costs by 20x. Supports hybrid mode with Set-of-Mark numbered overlays so vision models can ground elements visually. Ships with Mozilla Readability extraction, residential proxy rotation with sticky session templates, Bezier-curve mouse movements, and CapSolver/2Captcha fallback. Useful when you need to automate interactions on protected sites you own or have permission to test, with a fingerprint that matches real Chrome at the TLS and DOM layers.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

stealth-agent-browser-mcp

A Model Context Protocol (MCP) server that gives AI agents a stealth-grade Chromium browser with a hybrid Accessibility-Object-Model + Set-of-Mark vision interface. Built for Claude, works with any MCP-compatible host.

  • Stealth first. Uses rebrowser-playwright to patch the Runtime.Enable CDP leak that bypasses playwright-extra-class stealth plugins. Passes modern bot-detection suites (CreepJS, bot.sannysoft.com) where vanilla Playwright fails.
  • Token-lean by default. browser_snapshot returns Playwright aria snapshot YAML (~2–5 KB) instead of raw HTML (100KB+). Every interactive element carries a [ref=eN] id that actions consume directly — no selectors, no drift.
  • Hybrid vision when it matters. Ask for mode: "hybrid" and the server overlays numbered red boxes on the screenshot so the model can ground visually (Set-of-Mark prompting, Yang et al.). The ref ids on the image match the ids in the YAML. No parallel numbering scheme to go out of sync.
  • Readability-based content extraction. browser_scroll_read runs Mozilla Readability through JSDOM and returns clean Markdown — optionally delta-only, so re-reads cost nothing when nothing changed.
  • Proxy-ready. Per-session proxy auth, useful with residential pools.

Authorized use only. Stealth tooling has legitimate applications (accessibility auditing, your-own-account automation, QA against sites you own or have permission to test). Do not use this server to violate a site's terms of service or applicable law. See SECURITY.md.


Install

npm install -g stealth-agent-browser-mcp
# Chromium binary is fetched automatically on first launch
npx playwright-core install chromium

Or run without install via npx stealth-agent-browser-mcp.

Quickstart (Claude Desktop / Claude Code / Cursor)

Add to your MCP config:

{
  "mcpServers": {
    "stealth-browser": {
      "command": "npx",
      "args": ["-y", "stealth-agent-browser-mcp"],
      "env": {
        "SAB_HEADLESS": "true",
        "SAB_STEALTH_LEVEL": "patched"
      }
    }
  }
}

Restart the host. The agent will see the tools listed below.

Tools

ToolPurpose
browser_navigateNavigate a URL and return a snapshot.
browser_snapshotaom (YAML only, cheapest), vision (raw screenshot), or hybrid (YAML + Set-of-Mark screenshot).
browser_clickClick an element by its [ref=eN].
browser_typeType into an input/textarea by ref.
browser_selectChoose options in a <select> by ref.
browser_scroll_readScroll and return Readability Markdown (delta-only by default).
browser_wait_forWait for text or a ref to become visible.
browser_tabslist / new / close / switch.
browser_evalEvaluate a JS expression in the page's MAIN world; JSON result.
browser_set_proxyUpdate single-proxy config (effective after browser_restart).
browser_set_proxy_poolReplace residential proxy pool at runtime (effective after browser_restart).
browser_solve_captchaFallback captcha solver (CapSolver / 2Captcha). Detects Turnstile/hCaptcha/reCAPTCHA on the page.
browser_restartClose + re-open the active browser session with current config.

All action tools are addressed by the ref emitted in the last AOM snapshot. Refs are Playwright's own aria-ref=eN ids — there is no parallel numbering scheme.

Configuration

All via environment variables:

VarDefaultNotes
SAB_HEADLESStruefalse for a visible window (debugging).
SAB_STEALTH_LEVELpatchedoff | patched | paranoid.
SAB_PROXY_SERVER—Single-proxy mode. e.g. http://host:port
SAB_PROXY_USERNAME / SAB_PROXY_PASSWORD—
SAB_PROXY_POOL—Residential pool. Comma-separated URLs (http://u:p@host:port,...) or a JSON array of {server, username, password}.
SAB_PROXY_ROTATIONper-restartper-session | per-restart | static.
SAB_PROXY_STICKY_TEMPLATE—Username template for sticky-IP providers. ${sessionId} interpolates. Example: brd-customer-c1-zone-res-session-${sessionId}.
SAB_HUMAN_MOUSEtrueBezier-path click with pre-click hesitation. Defeats Datadome trajectory analysis.
SAB_CAPTCHA_PROVIDERnonecapsolver | twocaptcha | none.
SAB_CAPTCHA_API_KEY—Provider API key.
SAB_USER_DATA_DIR—Persistent profile directory (cookies build reputation).
SAB_DEFAULT_TIMEOUT_MS15000Per-action timeout.
SAB_MAX_ANNOTATED75Max labelled boxes in hybrid mode.
SAB_VIEWPORT_W / SAB_VIEWPORT_H1366 / 768
SAB_LOCALEen-US
SAB_TIMEZONEAmerica/New_York
LOG_LEVELinfodebug, warn, etc. Always writes to stderr.

Architecture

src/
├── index.ts         # Entry (stdio)
├── server.ts        # MCP server + tool registration
├── tools.ts         # Tool handlers
├── browser.ts       # Stealth Chromium launcher (rebrowser-playwright)
├── session.ts       # Per-connection browser/context/page state
├── snapshot.ts      # AOM + Set-of-Mark pipeline
├── annotate.ts      # SVG overlay compositing (sharp)
├── reader.ts        # Readability → Markdown (pierces open shadow roots)
├── fingerprint.ts   # Rotatable UA/viewport/timezone profiles
├── proxy.ts         # Residential pool + rotation + sticky-session template
├── human-mouse.ts   # Bezier-curve cursor paths (ghost-cursor math)
├── captcha.ts       # CapSolver / 2Captcha REST adapters
├── config.ts        # Zod-validated env config
└── logger.ts        # pino → stderr (never stdout)

All logs go to stderr — stdout is reserved for JSON-RPC. Never add console.log.

TLS / JA3 fingerprint — why there is no Node-layer spoofer here

A common ask for scrapers is: "spoof the TLS ClientHello (JA3) to look like Chrome, via curl-impersonate or node-tls-client."

That applies to Node-layer HTTP scrapers (fetch, got, axios) where the TCP connection originates from Node's OpenSSL, which emits a ClientHello signature distinct from Chrome's BoringSSL — and Cloudflare / Akamai Bot Manager drop it at the network layer before a single byte of JavaScript runs.

This MCP does not have that architecture. Every request exits through Chromium. Chromium's TLS stack is Chrome's TLS stack (literally the same BoringSSL build), so the ClientHello JA3 is Chrome's JA3 by construction. No JS-level rewriting is possible or necessary.

The one place TLS can still betray you is if you route through a proxy that terminates and re-initiates TLS (MITM). Residential proxy providers (Bright Data, DataImpulse, Oxylabs residential, SOAX) route at TCP — they do not MITM TLS — and the Chromium handshake reaches the origin unmodified. The products that do MITM TLS are managed scraping browsers (Bright Data's Scraping Browser, Oxylabs Web Unblocker), which ship their own headless Chrome and replace this MCP rather than layering on top of it.

Bottom line: with rebrowser-playwright + residential pool (P1) + human mouse (P2), the TLS fingerprint, CDP runtime, DOM surface, and behavioral layer all match real Chrome. Captcha solving (P3) is a fallback for the 1–5% of sessions that still get flagged.

Benchmarks

npm run bench:stealth launches the configured browser against public bot-detection test pages (bot.sannysoft.com, CreepJS, pixelscan, BrowserLeaks WebRTC) and reports pass/fail. These are the same harnesses used by the rebrowser-patches and Patchright projects — see rebrowser-bot-detector for the reference suite.

Typical local-fixture test run (see test/):

TestResult
AOM YAML contains refs for all interactive elements✓
hybrid mode returns PNG + YAML, refs match✓
click/type by ref produces expected DOM change✓
Readability extracts article to Markdown✓
Delta-only scroll returns (no readable content change) on repeat✓

Comparison

stealth-agent-browser-mcpplaywright-mcpbrowser-use MCPcomputer use
CDP-level stealth (Cloudflare/DataDome)✓✗partial✗
Accessibility-tree snapshots✓✓✓✗
Set-of-Mark vision (ref-labeled screenshot)✓✗✗pure vision
Readability-based scroll-and-read✓✗✗✗
Token-lean by default✓✓✗✗
Bundled agent loop✗ (host's model drives)✗✓✗

Development

npm install
npx playwright-core install chromium
npm run build
npm test

Contributing

See CONTRIBUTING.md. All contributions under Apache-2.0.

License

Apache-2.0

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Configuration

SAB_HEADLESSdefault: true

Run Chromium headless. Default: true.

SAB_STEALTH_LEVELdefault: patched

off | patched | paranoid. Default: patched.

SAB_PROXY_SERVER

Optional proxy URL, e.g. http://host:port.

SAB_PROXY_USERNAMEsecret

Optional proxy username.

SAB_PROXY_PASSWORDsecret

Optional proxy password.

SAB_USER_DATA_DIR

Persistent browser profile directory.

Categories
Web & Browser AutomationAI & LLM Tools
Registryactive
Packagestealth-agent-browser-mcp
TransportSTDIO
AuthRequired
UpdatedApr 14, 2026
View on GitHub

Related Web & Browser Automation MCP Servers

View all →
Browser Use

therealtimex/browser-use

AI browser automation - navigate, click, type, extract content, and run autonomous web tasks
Fetcher

jae-jae/fetcher-mcp

Fetch web page content using a Playwright headless browser with intelligent content extraction and Markdown/HTML output.
1k
Puppeteer

merajmehrabi/puppeteer-mcp-server

This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.
449
Playwright Mcp Server

com.thenextgennexus/playwright-mcp-server

Headless browser primitives for AI agents when sites need real JS rendering.
Browser

saik0s/mcp-browser-use

Provides a browser automation MCP server that lets AI assistants control a real browser for navigation, form interaction, data extraction, and more.
933
Browser Use

kontext-dev/browser-use-mcp-server

Browse the web, directly from Cursor etc.
822