Proxy4agents MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/novadalabs-proxy4agents-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

7 read · 0 write · 0 delete · 3 not yet classified

Secrets

11 (API keys, tokens or passwords)

Install scripts

Not scanned yet

Runs as

Node.js package

Tools (10)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• novada_proxy_batch_fetch

  Fetch multiple URLs concurrently through residential proxy. Returns structured JSON with per-URL results including ok/error status. Up to 20 URLs, up to 5 concurrent. WHEN TO USE: Scraping lists of URLs from search results, product catalogs, competitor pages. USE novada_proxy_fetch INSTEAD FOR: Single URLs — lower overhead. ON FAILURE: Individual URL failures are captured in results[].error — the batch itself succeeds even if some URLs fail.

• novada_proxy_crawl

  Crawl a website recursively via BFS from a starting URL to configurable depth. Returns all discovered URLs with metadata, page titles, and optionally page content + extracted fields inline. WHEN TO USE: Full-site scraping, sitemap generation, content indexing, competitive analysis — when you need MORE than a single page. USE novada_proxy_map INSTEAD IF: You only need links from ONE page. USE novada_proxy_batch_fetch INSTEAD IF: You already have the URLs and just need content. WORKFLOW: crawl(url, max_pages=20, max_depth=3, include_content=true) → get full site content in one call. FILTERING: …

• novada_proxy_extract

  Extract structured fields (title, price, rating, author, etc.) from any URL via residential proxy. Returns JSON with ok, data.fields as key-value map. Uses Open Graph, JSON-LD, and HTML heuristics. WHEN TO USE: Product pages, articles, listings where you need specific fields not raw content. USE novada_proxy_fetch INSTEAD IF: You need full page content, not specific fields. AUTO-ESCALATION: Set render_fallback:true to automatically retry via real browser if proxy fetch fails. Costs 5 credits if escalated. ON FAILURE without render_fallback: If TLS_ERROR or BOT_DETECTION_SUSPECTED → retry with…

• novada_proxy_fetch

  Fetch any URL through residential proxy (2M+ IPs, 195 countries, anti-bot bypass). Returns JSON: ok, data.content, data.status_code, meta.latency_ms, meta.cache_hit. WHEN TO USE: Static/HTML pages, Amazon, LinkedIn, news sites, most commercial sites. USE novada_proxy_render INSTEAD IF: Page requires JavaScript to load (SPAs, React/Vue apps, dynamic feeds). USE novada_proxy_extract INSTEAD IF: You need structured fields (title, price, rating) not raw content. ON FAILURE: If error.code is BOT_DETECTION_SUSPECTED → retry with novada_proxy_render. If TLS_ERROR → retry with a different country par…

• novada_proxy_map

  Crawl a URL and return all internal links found on the page. Returns structured JSON with data.internal_urls array. Useful for discovering pages before batch-fetching them. WHEN TO USE: Before a batch scraping job — call novada_proxy_map first to discover URLs, then novada_proxy_batch_fetch to scrape them. USE novada_proxy_fetch INSTEAD IF: You only need the content of a single specific URL. NOTE: This is a shallow map (single page). For deep crawls, call novada_proxy_map iteratively on discovered URLs. ON FAILURE: If too few links found, the page may use JavaScript to load navigation — retry…

• novada_proxy_render

  Render a JavaScript-heavy page with real Chromium [BETA]. Returns structured JSON with ok, data.content. Requires NOVADA_BROWSER_WS env var. WHEN TO USE: SPAs, React/Vue apps, infinite scroll, pages that require JS to load content. USE novada_proxy_fetch INSTEAD FOR: Static HTML pages — it is 3-5x faster. ON FAILURE: If error.code is TIMEOUT → increase timeout. If PROVIDER_NOT_CONFIGURED → set NOVADA_BROWSER_WS.

• novada_proxy_research

  Research a topic by searching the web, fetching top results, and returning structured findings with sources. The findings_summary concatenates source previews — your agent should analyze findings[] for deeper synthesis. WHEN TO USE: Research questions, topic investigation, competitive analysis, fact-finding. USE novada_proxy_search INSTEAD IF: You just need search results (titles + URLs), not full content. USE novada_proxy_fetch INSTEAD IF: You already know which URL to read. CHAIN WITH: The findings_summary is a starting point — use novada_proxy_fetch on specific urls[] for deeper reading. O…

• novada_proxy_search

  Search Google and return structured results (title, url, snippet) as JSON. No HTML parsing needed — results are pre-structured. WHEN TO USE: Finding pages by topic, factual queries, discovering URLs to then fetch. USE novada_proxy_fetch INSTEAD FOR: Reading a specific URL you already have. ON FAILURE: If error.code is PROVIDER_NOT_CONFIGURED → set NOVADA_API_KEY.

• novada_proxy_session

  Fetch a URL with sticky-session IP persistence and optional verification. For basic sticky routing without verification, use novada_proxy_fetch with session_id instead. Reuses the same residential IP across calls with the same session_id. Returns structured JSON. Use verify_sticky:true to confirm the session held. WHEN TO USE: Multi-step workflows where IP consistency matters: login flows, paginated scraping, price monitoring. NOTE: Sticky sessions are best-effort — infrastructure may not guarantee 100% IP consistency. Use verify_sticky:true to confirm. NOTE: verify_sticky:true makes 3 seque…

• novada_proxy_status

  Check proxy connectivity and provider health. Returns structured JSON with ok, data.connectivity.status (HEALTHY/DEGRADED/UNAVAILABLE) and data.connectivity.proxy_ip (verified via live proxy call). WHEN TO USE: Before starting a large scraping workflow, or to diagnose proxy failures. NOTE: Live connectivity check — makes one proxy request to httpbin.org/ip on every call. USE novada_proxy_fetch INSTEAD IF: You need to test fetching a specific URL, not general proxy health. ON FAILURE: If PROVIDER_NOT_CONFIGURED → set proxy credentials env vars. If UNAVAILABLE → check provider dashboard.

Signals

Stars

4

Forks

1

Open issues

0

Last commit

Jun 18, 2026 (4 months ago)

Last release

Apr 13, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name

io.github.NovadaLabs/proxy4agents-mcp

Version

1.7.0

Auth

API key

Packages

npm bestproxy4agents-mcp

License

MIT

Repository

github.com/NovadaLabs/proxy4agent

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql