Stealth Browser Gateway

面向 AI agents 的反检测浏览器：抓取会屏蔽普通无头浏览器的页面并运行点击场景；返回 HTML、文本或 JSON。仅为成功抓取的页面付费。通过 Apify 使用远程 MCP。

托管 MCP 服务器

npx add-mcp 'https://mcp.apify.com?tools=titan_coder/stealth-browser-gateway'

可安装到 Claude Code、Codex、Cursor 等客户端

文档

Stealth Browser Gateway: anti-detect browser API for AI agents (MCP) and scraping

An Apify Actor that opens web pages in an anti-detect Firefox-based browser and returns clean HTML, visible text or embedded JSON (__NEXT_DATA__, JSON-LD). It can also run click-by-click scenarios and capture network responses. Use it from Python, JavaScript, curl, n8n, Make, LangChain, or as an MCP tool in Claude, Cursor and Windsurf.

You pay $0.002 per successfully scraped page ($0.02 per completed interactive scenario). Blocked and failed pages are not charged. Proxies are optional and paid by you (your Apify account or your own proxy provider).

Measured results (1 Nov 2026, Apify cloud, no proxy, 5 attempts per site)

Success means real content came back (products, listings, price data), not just HTTP 200.

Site	Protection	Success
Zillow listing, Walmart search, Fiverr category, Vinted catalog	PerimeterX / DataDome	5/5
Facebook Ads Library (with `successRequires`)	Meta	5/5
TikTok Explore	in-house	3/5
Upwork job search	Cloudflare	1/5
G2, Tripadvisor, Indeed	DataDome / Cloudflare	0/5 (datacenter IPs blocked; bring a residential proxy)

Interactive CAPTCHAs are not solved. Use public pages only and respect each site's terms.

Use it as an MCP tool

Hosted (OAuth):

{
  "mcpServers": {
    "stealth-browser-gateway": {
      "url": "https://mcp.apify.com?tools=titan_coder/stealth-browser-gateway"
    }
  }
}

Local (stdio):

{
  "mcpServers": {
    "stealth-browser-gateway": {
      "command": "npx",
      "args": ["-y", "@apify/actors-mcp-server", "--actors", "titan_coder/stealth-browser-gateway"],
      "env": { "APIFY_TOKEN": "<YOUR_APIFY_TOKEN>" }
    }
  }
}

Quick start (Python)

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("titan_coder/stealth-browser-gateway").call(run_input={
    "startUrls": [{"url": "https://www.walmart.com/search?q=headphones"}],
    "extractMode": "html",
})
for page in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(page["url"], page["status"], page["ok"])

Full documentation, input options and pricing: https://apify.com/titan_coder/stealth-browser-gateway