/ Diretório / Playground / stealth-browser-mcp
● Comunidade vibheksoni ⚡ Instantâneo

stealth-browser-mcp

por vibheksoni · vibheksoni/stealth-browser-mcp

90-tool MCP browser automation that bypasses anti-bot systems — network hooks, UI cloning, and CDP control via natural language.

stealth-browser-mcp is an MCP server for undetectable browser automation using nodriver and Chrome DevTools Protocol. It provides 90 tools across 11 categories: browser management, element interaction, pixel-perfect UI cloning, network debugging with dynamic hooks, CDP functions, progressive cloning, cookies/storage, tabs, and page analysis. Bypasses Cloudflare and similar protections. Works with Claude, Cursor, and other MCP clients.

Por que usar

Principais recursos

Demo ao vivo

Como fica na prática

stealth-browser-mcp.replay ▶ pronto
0/0

Instalar

Escolha seu cliente

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "stealth-browser-mcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/vibheksoni/stealth-browser-mcp"
      ]
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "stealth-browser-mcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/vibheksoni/stealth-browser-mcp"
      ]
    }
  }
}

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "stealth-browser-mcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/vibheksoni/stealth-browser-mcp"
      ]
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "stealth-browser-mcp": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/vibheksoni/stealth-browser-mcp"
      ]
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "stealth-browser-mcp",
      "command": "TODO",
      "args": [
        "See README: https://github.com/vibheksoni/stealth-browser-mcp"
      ]
    }
  ]
}

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json
{
  "context_servers": {
    "stealth-browser-mcp": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/vibheksoni/stealth-browser-mcp"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add stealth-browser-mcp -- TODO 'See README: https://github.com/vibheksoni/stealth-browser-mcp'

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: stealth-browser-mcp

How to scrape data from a Cloudflare-protected site for authorized research

👤 Researchers and data analysts who need data from protected sites they have permission to access ⏱ ~15 min intermediate

Quando usar: You need to extract data from a site you're authorized to access but standard scraping tools get blocked.

Pré-requisitos
  • stealth-browser-mcp installed — Clone repo, pip install -r requirements.txt
  • Authorization to access the target site — Ensure you have permission to scrape the site
Fluxo
  1. Navigate to the site
    Open a stealth browser and navigate to https://example.com/data. Wait for the page to fully load.✓ Copiado
    → Page loaded successfully, bypassing protection
  2. Extract data
    Query all elements matching the product listing cards. Extract titles, prices, and URLs.✓ Copiado
    → Structured data from the page

Resultado: Data extracted from the protected site for authorized analysis.

Armadilhas
  • Running too many concurrent browsers — Keep to 1-2 browser instances at a time to avoid detection patterns
Combine com: filesystem

Clone a UI element pixel-perfect for design reference

👤 Frontend developers who want to study and replicate a UI pattern ⏱ ~10 min intermediate

Quando usar: You see a UI component you like and want the complete HTML/CSS for reference.

Pré-requisitos
  • stealth-browser-mcp running — Start the MCP server
Fluxo
  1. Navigate and identify
    Open https://example.com and take a screenshot. I want to clone the navigation header.✓ Copiado
    → Screenshot with page rendered
  2. Clone the element
    Clone the nav header element completely — HTML structure, CSS styles, events, and animations. Save to a file.✓ Copiado
    → Complete element clone saved with all styles and assets

Resultado: A self-contained HTML/CSS clone of the UI element for reference.

Armadilhas
  • Cloned elements may depend on external fonts or scripts — Use extract_element_assets to also capture referenced resources
Combine com: filesystem

Combinações

Combine com outros MCPs para 10× de alavancagem

stealth-browser-mcp + filesystem

Save scraped data and cloned UI elements to organized files

Scrape all product data from the page and save it as JSON to ~/data/products.json.✓ Copiado

Ferramentas

O que este MCP expõe

FerramentaEntradasQuando chamarCusto
spawn_browser options?: obj Launch a new stealth browser instance 0
navigate url: str Navigate to a URL 0
query_elements selector: str Find elements by CSS selector 0
clone_element_complete selector: str Pixel-perfect clone of a DOM element with all styles 0
create_dynamic_hook hook_function: str Create a Python function to intercept network traffic 0
take_screenshot selector?: str Capture a screenshot of the page or specific element 0
execute_script script: str Execute JavaScript in the page context 0

Custo e limites

O que custa rodar

Cota de API
N/A — runs locally
Tokens por chamada
200–2000 tokens per tool call
Monetário
Free
Dica
Use core mode (22 tools) if your client struggles with the full 90-tool set.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: No credentials stored by the server. If accessing authenticated sites, manage cookies via get/set_cookie tools.
Saída de dados: Connects to whatever URLs you navigate to via Chrome

Solução de problemas

Erros comuns e correções

Chrome not found

The server uses nodriver which manages its own Chrome. Ensure Chrome is installed or let nodriver download it.

Verificar: which google-chrome || which chromium
Anti-bot detection still triggered

Try adding delays between actions, reduce concurrent requests, or use different browser profiles.

Verificar: Check the page for CAPTCHA or block messages
Element clone incomplete

Some elements use shadow DOM or iframe isolation. Use execute_cdp_command for low-level access.

Verificar: Inspect the element in DevTools to check for shadow roots

Alternativas

stealth-browser-mcp vs. outros

AlternativaQuando usarTroca
playwright MCPYou don't need anti-bot bypass and want standard browser automationStandard Playwright with no stealth features but broader community support

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills