Proxy4agents MCP
The agent-first residential proxy MCP - works with any provider. Route any HTTP request through 2M+ real home devices - Android phones, Windows PCs, Macs - to bypass anti-bot systems, geo-target by country or city, and maintain sticky sessions across multi-step workflows. Powered by Novada . Its 9 documented tools cover novada, proxy. It runs locally over stdio via the published package.
People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.
VERIFIED ACTIVE
LAST COMMIT 2026-06-18 · ★ 4 · #46 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25
MIT · JavaScript servers · how we verify → /methodology
01 · Install Proxy4agents MCP
before you install - you'll need
Set NOVADA_PROXY_USER, NOVADA_PROXY_PASS, NOVADA_API_KEY, NOVADA_BROWSER_WS, BRIGHTDATA_PASS, SMARTPROXY_USER, SMARTPROXY_PASS, OXYLABS_USER, OXYLABS_PASS, PROXY_URL before connecting. BRIGHTDATA_USER is optional or environment-specific per the README.
Claude Code
claude mcp add novadalabs-proxy4agent -- npx -y bestproxy4agents-mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"novadalabs-proxy4agent": {
"command": "npx",
"args": [
"-y",
"bestproxy4agents-mcp"
]
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as local process (stdio) - runs on your machine with your user's permissions
license MIT - declared in the repository
npm package bestproxy4agents-mcp - unscoped; check the name against the project README before installing
registry namespace io.github.NovadaLabs is GitHub-verified and matches the repo owner
03 · What Proxy4agents MCP can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
What you can build
An agent gets 9 documented tools spanning novada, proxy, including novada_proxy_fetch, novada_proxy_batch_fetch, novada_proxy_extract, novada_proxy_map.
The 9 tools it gives your agent
Extracted from the project's README - what proxy4agents-mcp lets an agent do.
- novada_proxy_fetch
- - Fetch any URL through a residential proxy. Returns structured JSON with content, status code, and metadata. Auto-retry on network errors. Caches repeated calls
- novada_proxy_batch_fetch
- - Fetch 2–20 URLs concurrently through residential proxy. Up to 5x faster than sequential fetches. Per-URL errors are captured individually - the batch itself suc
- novada_proxy_extract
- - Extract structured fields from any URL using heuristic pattern matching (meta tags, Open Graph, JSON-LD, Schema.org). Lightweight - no LLM needed. Set render_fa
- novada_proxy_map
- - Crawl a URL and return all internal links as a structured JSON array. Use as the discovery step before novada_proxy_batch_fetch to crawl an entire site without
- novada_proxy_session
- - Sticky session fetch - every call with the same session_id uses the same residential IP. Essential for login flows, paginated scraping, and price monitoring. Su
- novada_proxy_search
- - Structured Google search via Novada Scraper API. Returns titles, URLs, and snippets as clean JSON - no HTML parsing needed.
- novada_proxy_crawl
- - Recursively crawl a website via BFS traversal. Starts from a URL, discovers links at each depth level, and returns the full URL tree with metadata.
- novada_proxy_research
- - One-shot research tool - searches the web, fetches top results, and returns structured findings with source previews. The agent can analyze the findings for dee
- novada_proxy_status
- - Check proxy network connectivity and version. Makes a live proxy call to verify the connection is working. No credentials required.
Latest releases
v1.7.1 · 2026-04-13
What's new in v1.7.1 · 3 new tools · agentproxy_batch_fetch - fetch 2–20 URLs concurrently (up to 5x parallel), per-item error capture · agentproxy_extract - structured field extraction (title, price, rating…), auto…
v1.7.0 · 2026-04-10
What's New · New Tool: agentproxy_extract · Extract structured data from any URL - title, price, description, rating, author, date, image, links, headings. Uses meta tags, Open Graph, JSON-LD, and HTML pattern…
v1.5.0 · 2026-04-09
Multi-provider residential proxy MCP server. See proxy-veil on npm. · Novada, BrightData, Smartproxy, Oxylabs, and any HTTP proxy.
04 · Who maintains Proxy4agents MCP
proxy4agents-mcp is maintained by novadalabs. It's the only MCP server we track from this author; the repo dates to Apr 2026.
05 · Facts
- repository
- github.com/novadalabs/proxy4agent
- category
- web scraping - ranked #46 of 78 actively-maintained web scraping servers as of 2026-08-25.
- registry
- io.github.NovadaLabs/proxy4agents-mcp (active, first published 2026-04-10)
- packages
- npm:bestproxy4agents-mcp
06 · Proxy4agents MCP FAQ
Is Proxy4agents MCP still maintained?
Yes - as of 2026-08-25, its last commit was 2026-06-18. We re-verify nightly.
What can Proxy4agents MCP do?
An agent gets 9 documented tools spanning novada, proxy, including novada_proxy_fetch, novada_proxy_batch_fetch, novada_proxy_extract, novada_proxy_map.
How do I install Proxy4agents MCP?
Run `npx -y bestproxy4agents-mcp`. The README documents 11 environment variables (NOVADA_PROXY_USER, NOVADA_PROXY_PASS, NOVADA_API_KEY…) to set first. Set NOVADA_PROXY_USER, NOVADA_PROXY_PASS, NOVADA_API_KEY, NOVADA_BROWSER_WS, BRIGHTDATA_PASS, SMARTPROXY_USER, SMARTPROXY_PASS, OXYLABS_USER, OXYLABS_PASS, PROXY_URL before connecting. BRIGHTDATA_USER is optional or environment-specific per the README. You can also paste the ready-made client config above.
Does Proxy4agents MCP run locally?
Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.
07 · Alternatives to Proxy4agents MCP
Alternatives to Proxy4agents MCP
Maintained web scraping servers if Proxy4agents MCP isn't the fit.
- Firecrawl MCP Server MCP server for Firecrawl - web search, scraping, and biomedical/arXiv paper search. ★ 7,310 · 2026-08-25
- Exa Fast, intelligent web search and web crawling. New mcp tool: Exa-code is a context tool for coding ★ 4,917 · 2026-08-21
- Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ ★ 4,718 · 2026-08-23
- Wigolo Local-first web intelligence MCP server for AI coding agents ★ 4,647 · 2026-08-24
- Tavily MCP MCP server for advanced web search using Tavily ★ 2,351 · 2026-08-20
- Open Brand Extract brand assets (logos, colors, backdrop images, brand name) from any website URL ★ 785 · 2026-05-12
Pairs well with
Servers that cover what Proxy4agents MCP doesn't - only shown when the pairing reason fits the companion.
- SearXNG Search → search companion search · ★ 1,158
- Blockrun MCP → search companion search · ★ 388
- Supabase → database companion database · ★ 2,871
- MongoDB MCP Server → database companion database · ★ 1,106
- Codebase Memory → memory companion memory · ★ 40,198
- Memorix → memory companion memory · ★ 688
More web scraping MCP servers · Octen MCP · Scraper · Outscraper MCP Server · Web Page Fetcher · Parseur
More JavaScript MCP servers · Monerometrics · Server Json · Occasio · Sheetsdata MCP · Real Browser · see all