novada-proxy

Novada Proxy — Skill for Claude Code

When to Use This Skill

• Fetching URLs that block direct requests (Cloudflare, Akamai, DataDome)
• Scraping e-commerce, news, or professional sites (Amazon, LinkedIn, etc.)
• Extracting structured fields (title, price, rating) without HTML parsing
• Researching topics (search + batch read pipeline)
• Crawling entire sites (discover URLs + parallel fetch)
• Accessing geo-restricted content from 195+ countries
• Multi-step flows requiring the same IP (login, pagination)
• Rendering JS-heavy SPAs that return blank with standard HTTP

Setup

# Core (proxy fetch)
claude mcp add novada-proxy-mcp \
  -e NOVADA_PROXY_USER=your_username \
  -e NOVADA_PROXY_PASS=your_password \
  -- npx -y novada-proxy-mcp

# All tools (proxy + search + browser render)
claude mcp add novada-proxy-mcp \
  -e NOVADA_PROXY_USER=your_username \
  -e NOVADA_PROXY_PASS=your_password \
  -e NOVADA_API_KEY=your_key \
  -e NOVADA_BROWSER_WS=your_wss_url \
  -- npx -y novada-proxy-mcp

Credentials: novada.com -> Dashboard -> Residential Proxies

Tool Decision Tree

Need to fetch a URL?
  Static HTML page             -> novada_proxy_fetch
  Need specific fields         -> novada_proxy_extract
  JS-heavy / SPA / blank page  -> novada_proxy_render (5 credits)

Need multiple URLs?
  Have the URLs already        -> novada_proxy_batch_fetch (2-20 URLs, up to 5x parallel)
  Need links from ONE page     -> novada_proxy_map -> novada_proxy_batch_fetch
  Need to crawl a whole site   -> novada_proxy_crawl (recursive BFS, depth 1-5)

Need to find URLs by topic?    -> novada_proxy_search -> novada_proxy_batch_fetch

Need research on a topic?      -> novada_proxy_research (search + read + summarize)

Need same IP across calls?     -> novada_proxy_session (sticky IP via session_id)

Need to check connectivity?    -> novada_proxy_status

Tools Reference

Tool	Purpose	Credits	Key Params
novada_proxy_fetch	Fetch single URL via residential proxy	1	url, country, format, session_id
novada_proxy_batch_fetch	Fetch 2-20 URLs concurrently	1/URL	urls, concurrency (1-5), country
novada_proxy_extract	Extract structured fields from URL	1 (5 if render fallback)	url, fields[], render_fallback
novada_proxy_map	Discover all internal links on a page	1	url, limit (10-200)
novada_proxy_crawl	Recursive site crawl (BFS, depth 1-5)	1/page	url, depth (1-5), limit, include_content
novada_proxy_session	Sticky session (same IP across calls)	1 (3 if verify)	session_id, url, verify_sticky
novada_proxy_search	Google search as structured JSON	1	query, num (1-20), country
novada_proxy_render	Render JS pages via real Chromium [BETA]	5	url, format, wait_for (CSS selector)
novada_proxy_research	Search + read + summarize on a topic	varies	query, num_sources (1-10), country
novada_proxy_status	Check proxy health + version	1	(none)