The web scraping MCP server for AI agents

A web scraping MCP server exposes web-data tools to an AI agent over the Model Context Protocol, so the model fetches live pages itself. QuanticData is one MCP server for all of them: search, scrape, crawl, map, batch and seo_audit, routed through residential proxies and billed only on success.

Get my free API key Install in one command

$1 free every month · No card required · Pay per success

mcp · agent session

# the agent picks each tool on its own
tool call · search
  { "query": "best vector db 2026", "engine": "google" }
→ organic[10] · related_questions[4] · ai_overview
tool call · scrape
  { "url": "https://acme.dev/pricing", "format": "markdown" }
→ "# Acme — from $49/mo · usage $0.0002"
tool call · crawl
  { "url": "https://docs.acme.dev", "depth": 2 }
→ job started · 48 pages · poll crawl_status

8 MCP toolssearch · scrape · map · crawl · batch · seo_audit

Every AI clientClaude · Cursor · Windsurf · VS Code · Cline

Proxies underneathevery call exits a residential IP

Pay per successblocks, timeouts & retries are free

What is an MCP server?

An MCP server is a program that exposes tools and data to an AI client over the Model Context Protocol — an open standard for connecting models to the outside world. The server declares each tool with a typed schema; the model reads those schemas and decides when to call one. Connect a server once and the agent gains its capabilities, with no per-framework glue code.

A web scraping MCP server puts the open web behind those tools. Instead of guessing about a page it has never seen, the agent calls a tool, gets clean content back, and reasons over it in the same turn. QuanticData's server does that for search, single pages and whole sites — over a residential proxy network, so bot walls stay the server's problem, not the model's.

AI Overview

What is a web scraping MCP server?

A web scraping MCP server is a Model Context Protocol server that hands an AI agent tools to fetch, search and read live web pages autonomously. QuanticData exposes eight of them from one server, so a model can run a search, scrape a page, or crawl a whole site mid-conversation — and get back token-efficient Markdown or structured JSON.

One server, every tool: search, scrape, map, crawl, batch and seo_audit — not just single-page fetching.
Proxies built in: every call routes through residential, mobile, datacenter or IPv6 exits with anti-bot handling.
LLM-shaped output: clean Markdown, SerpApi-compatible SERP JSON, and a usage block on every response.
Pay per success: failed calls and internal retries are never billed; $1 of free usage every month, no card.

Jump to The tools Install Pricing

Every web-data tool, one MCP server

Competitors expose scraping alone. QuanticData gives your agent the whole surface — search, scrape, crawl, map, batch and audit — behind eight tools with the real names and parameters from the package. Every one runs over the proxy network beneath it.

`search`

Google, Bing and DuckDuckGo across 17 verticals — web, images, news, shopping, maps, scholar, jobs, flights, hotels, lens and more. SerpApi-compatible JSON. Key params: query, engine, search_type, country, num.

`scrape`

One page to clean Markdown, HTML or text with a real Chrome TLS fingerprint. Run CSS or plain-language extraction inline. Key params: url, format, content_mode (smart/article/full), engine, extract, ai_prompt.

`map`

Discover a site's URLs fast from robots sitemaps and homepage links — no full crawl. Up to 5,000 URLs plus a site-wide total. Key params: url, limit, search (substring filter), group_by.

`crawl`

Start an async breadth-first crawl from a seed URL, each page converted to Markdown. Depth up to 10, include/exclude globs. Key params: url, limit, depth, content_mode, include, exclude. Returns a job id.

`crawl_status`

Poll a crawl job for progress and the pages gathered so far, so long crawls never blow the context window. Key param: jobId. Unused pages on a finished job are refunded automatically.

`batch`

Scrape up to 1,000 URLs asynchronously with shared options. Set mode: "summary" for metadata-only audits. Key params: urls, format, content_mode, engine, country. Returns a job id.

`batch_status`

Poll a batch job incrementally — pass the previous nextCursor as since to receive only new items. Key params: jobId, since, include_content. Content is omitted by default to stay light.

`seo_audit`

Fetch a URL twice — as a no-JS bot and fully rendered — and return both views plus the diff and bot-facing meta (robots, Open Graph, JSON-LD). Key params: url, country, no_render.

MCP for proxies, too — every call exits a residential IP

Each tool call routes through QuanticData's own residential, mobile, datacenter and IPv6 networks, with browser escalation when a target fights back. Add country to any call to pin the exit. Want raw transport instead of finished data? The same networks are sold as plain proxies under one account.

See the proxy networks

Works in every AI client and framework

Any MCP-capable client connects natively — Claude Desktop, Claude Code, Cursor, Windsurf, VS Code and Cline pick up all eight tools the moment you add the config. Point ChatGPT's connectors at the same server, or wrap the tools in an agent framework: LangChain, LlamaIndex, CrewAI and the OpenAI Agents SDK take a few lines each.

Prefer no code? n8n and Zapier call the same REST endpoints from an HTTP node — one JSON envelope throughout, so what you prototype in Claude behaves identically in production. Need just one capability? The SERP API and the web scraping API stand alone, and the web data API for AI covers the full agent surface.

Setup

Add the MCP server in one command

The server is a small local package launched with npx — it talks to the hosted API with your key, so there are no internal secrets and nothing to deploy. Set QUANTUMPROXIES_API_KEY and restart the client.

claude mcp add quantumproxies \
  -e QUANTUMPROXIES_API_KEY=qp_live_your_key_here \
  -- npx -y quantumproxies-mcp

# eight tools appear: search, scrape, map, crawl,
# crawl_status, batch, batch_status, seo_audit

// claude_desktop_config.json
{
  "mcpServers": {
    "quantumproxies": {
      "command": "npx",
      "args": ["-y", "quantumproxies-mcp"],
      "env": {
        "QUANTUMPROXIES_API_KEY": "qp_live_your_key_here"
      }
    }
  }
}

// .cursor/mcp.json  (or VS Code / Windsurf mcp.json)
{
  "mcpServers": {
    "quantumproxies": {
      "command": "npx",
      "args": ["-y", "quantumproxies-mcp"],
      "env": {
        "QUANTUMPROXIES_API_KEY": "qp_live_your_key_here"
      }
    }
  }
}

Not using MCP? Every tool is also a plain REST endpoint with the same JSON envelope — see the web data API for AI for the REST shape.

Pricing

Pay-per-success, priced for agents

Agents probe, retry and dead-end by design — so failed tool calls are never billed, and every response tells the agent what it just spent. The server itself is free and open.

$0.0002per page scraped$0.001 with JS rendering

$0.0005per SERP search$0.002 with JS rendering

$0.0003per crawled pageasync, auto-refund on unused

$0.0002per batch URLup to 1,000 URLs per job

Pay as you go

$0/mo

$1 free credit / month
60 requests / min
List unit prices

Starter

$19/mo

$10 free credit / month
300 requests / min
10% off unit prices

Growth

$79/mo

$50 free credit / month
600 requests / min
20% off unit prices

Scale

$299/mo

$250 free credit / month
1,200 requests / min
30% off unit prices

Free & open server packageUsage cost in every responseFailed calls never billedAsync jobs auto-refund failuresOne key for tools and proxies

QuanticData MCP vs a typical scraping MCP

	QuanticData MCP	Typical scraping MCP
Tools exposed	8 — search, scrape, map, crawl, batch, seo_audit	1–3 — single-page fetch
Search / SERP	native search tool, 3 engines & 17 verticals	none
Whole-site jobs	async crawl, map & batch (up to 1,000 URLs)	one page at a time
Proxy network	4 in-house networks, country targeting	opaque or none
Billing	pay per success, failed calls free	credits per call
Output	one JSON envelope, SerpApi-compatible SERP	per-tool formats
Free tier	$1 every month, renews forever	one-time trial credits

FAQ

The short answers on pricing, formats and setup.

Something else? Ask us →

What is an MCP server?

An MCP server is a program that exposes tools and data to an AI client over the Model Context Protocol, an open standard. It declares each tool with a typed schema; the model decides when to call it. Connect one server and the agent gains those capabilities with no glue code.

What is a web scraping MCP server?

A web scraping MCP server gives an AI agent tools to fetch and read live web pages on its own. QuanticData exposes eight: search, scrape, map, crawl, crawl_status, batch, batch_status and seo_audit, so the model can search, read a page, or crawl a whole site mid-conversation.

How do I add the MCP server to Claude or Cursor?

Add one mcpServers block with the npx command and your QUANTUMPROXIES_API_KEY: paste it into claude_desktop_config.json for Claude Desktop, or .cursor/mcp.json for Cursor. In Claude Code run a single claude mcp add command. Restart the client and the eight tools appear.

Which AI clients and frameworks are supported?

Any MCP-capable client connects natively: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code and Cline. Frameworks like LangChain, LlamaIndex, CrewAI and the OpenAI Agents SDK wrap the tools in a few lines, and n8n or Zapier call the same REST endpoints from an HTTP node.

What tools does the MCP server expose?

Eight, from the real package: search (Google, Bing, DuckDuckGo across 17 verticals), scrape (a page to Markdown, HTML or text), map (fast URL discovery), crawl and crawl_status (async site crawls), batch and batch_status (up to 1,000 URLs), and seo_audit (no-JS versus rendered).

Is the MCP server free?

The server package is free and open, and every account gets $1 of usage each month with no card, enough for thousands of scrapes or searches. Beyond that you pay per successful call from $0.0002 per page. Blocked pages, captchas and retries are never billed.

MCP server vs API — what is the difference?

They are two front doors to the same platform. The REST API is called by your backend code; the MCP server lets the AI agent call the same tools itself, with typed schemas the model reads. Prototype through MCP, ship through REST, or use both — one key covers everything.

Can I self-host the MCP server, or is it hosted?

The MCP server runs locally as a small package you launch with npx, talking to the hosted QuanticData API with your key — no internal secrets and nothing to deploy. The heavy work (browsers, proxy rotation, retries, parsing) happens on our infrastructure, so your machine only carries the transport.

How is the MCP server billed?

Pay per success: each tool call is charged only when it returns a usable result, and every response carries a usage block with its cost. List prices are $0.0002 per scraped page, $0.0005 per search and $0.0003 per crawled page. Async crawl and batch jobs auto-refund unused pages.

Give your agent the whole web

$1 free every month, no card. Add the MCP server and let it search, scrape and crawl.

Get my free API key