Docs
Connect your agent →Log in
Live page fetch for AI agents

Ask for a page. Get the page.

DoubleCrawl gets your AI agent the pages its built-in fetch can't open. Add one tool, keep working, and pay only for pages that arrive.

5,000 free creditsNo credit cardFailed pages cost 0
Real page checkedor it costs 0
Level 2 · USlevel picked for you
200 OK · 4 creditsfailed pages cost 0
5,000free credits to start
$0for failed pages
1 toolto add to your agent
500requests at once on Scale

Works with

ClaudeChatGPTCursorWindsurfVS CodeGemini CLICodexZedLangChainVercel AI SDKCrewAIn8n
How it works

You ask. The page arrives.

Everything in between is our job: pick the level, retry when a page fails, and check that you got the real page.

01

Add it to your agent

One command in Claude Code, a minute anywhere else. It signs you in on first use and adds 5,000 free credits.

02

Ask for any page

When a page won't open, your agent reaches for DoubleCrawl. Or call POST /v1/request from your code.

03

We do the hard part

Right level, best route, automatic retries. Nothing to set up.

04

We check it's real

An error page isn't a page, and you don't pay for it. If it isn't the real page, we try again, on us.

05

You get the page

The site's own HTML, ready for your agent or parser. If it doesn't arrive, you don't pay.

For AI agents

Your agent got a 403. You got a copy-paste job.

It opens in your browser. It fails in your agent. So you paste the page into the chat by hand. DoubleCrawl is built to be found and set up from inside the chat, so the next fetch just works.

  • MCP serverClaude, ChatGPT, Cursor or any MCP client gets a fetch_page tool.
  • Sign in from the chatThe agent opens a sign-in link, you confirm, the key is connected.
  • See what happened on every pageEach response says if the page arrived and what it cost, so your agent can tell you.
  • Failed pages cost 0An agent that retries a failed page costs you nothing. We bill only delivered pages.
Connect your agent →
AIExample chatDoubleCrawl connected
Compare the 20 best-rated hotels in Lisbon and put them in a table.
fetch(hotels.example/lisbon) → 403
That page refused my fetch. I can get it through DoubleCrawl. It starts with 5,000 free credits, more than enough for this. Connect it?
Yes, do it.
Sign in here and I'll take it from there:
Connect DoubleCrawl →
doublecrawl.fetch_page(hotels.example/lisbon) → 200 delivered · 4 credits
Done. Here are the 20 hotels, sorted by rating ↓
Agents & developers

Plug it into your agent. Or any code.

Connect DoubleCrawl to Claude, ChatGPT, Cursor or your own agent over MCP. Prefer code? It's a single endpoint, no SDK required. You get the site's own page, and three headers tell you how it went.

HTTP/2 200
x-dd-target-outcome: delivered
x-dd-credits: 1
x-dd-request-id: 01JB7…QK
content-type: text/html; charset=utf-8
Your AI client
Claude.ai / Desktop
https://mcp.doublecrawl.com/mcp

No key yet? The server signs you in on first use and adds 5,000 free credits. Step-by-step guides →

Use cases

One tool for the pages your agent needs

Whatever you or your agent need from the web, DoubleCrawl brings back the real page.

AI agents & assistants

Give your agent live web access that doesn't stop at the first error page. Research and comparisons that actually finish.

Chat assistantsCoding agentsResearch agentsCustom agents

Price & stock monitoring

Track prices and availability across shops and marketplaces, in the countries you sell in.

MarketplacesRetailersD2C shops

Lead lists

Read thousands of company websites and score them against your ideal customer.

SalesLead genCRM

Knowledge bases

Live pages for your knowledge base or search index.

DocsNewsForums

Real estate & classifieds

New listings from property portals and classifieds, as often as you check.

Property portalsClassifiedsAuto

Reviews & brand monitoring

Follow reviews, ratings and mentions of your brand and your competitors.

Review sitesForums

Travel & tickets

Fares, rates and availability from booking sites, airlines and ticketing platforms.

AirlinesHotelsEventsCar rental

Your use case isn't here?

If your agent can't open a page, try it through DoubleCrawl.

Connect your agent →
Why not your own browser?

Public pages don't need your login

Browser tools are great for the apps you're logged into. Your agent doesn't need your account to read the rest of the web, and neither does your laptop.

Your browser

  • Your agent works on your logged-in account.
  • Your browser has to stay open.
  • An agent on a server can't reach it.
  • It opens pages one tab at a time.

DoubleCrawl

  • Your account never touches the site.
  • No browser to keep open.
  • It works from any server, n8n flow or hosted agent.
  • It runs up to 500 requests at once on Scale, more on Enterprise.

Keep your browser for the tools you're logged into. Send the rest of the web through DoubleCrawl.

Products

Fetch is live. The rest of the toolkit is next.

Fetch is ready today. Search, map, extract and interact are coming to the same account.

Fetch Live

Your agent asks for a URL and gets the page. Some pages still won't open. When that happens, you'll know, and you won't pay.

Country targeting Live

Pass a country code to see prices, results and stock as locals do.

Map Soon

List every page on a site before your agent reads a single one.

Join the waitlist →

Interact Soon

Click, type and scroll on a page, without your own browser.

Join the waitlist →

Extract Soon

Describe the fields in plain words and get JSON back.

Join the waitlist →

Markdown, screenshots, crawl Soon

More ways to read the web, on the same account.

Join the waitlist →

Join the waitlist

Accounts open soon. Pick what you want and we'll email you when it's ready, only about what you picked.

Products

You can withdraw any time. See the privacy policy.

Pricing

Pay for pages that arrive. Not for failed tries.

Start with 5,000 free credits. That's 5,000 pages at Level 1, 1,250 at Level 2 or 200 at Level 3. Every plan includes every level, country targeting and the MCP server. Plans differ mainly in credits and how many requests you can run at once, plus the extras listed on each plan.

Free

$0
one-time, no card
  • 5,000 credits≈ pages in totalLevel 15kLevel 21.25kLevel 3200
  • 5 concurrent requests
  • All levels
  • Country targeting & MCP
  • Community support
Start free

Start

$29/mo
$0.116 per 1,000 credits
  • 250,000 credits≈ pages a monthLevel 1250kLevel 262.5kLevel 310k
  • 20 concurrent requests
  • Top-ups at plan rate +15%
  • Email support
Choose Start

Growth

$99/mo
$0.099 per 1,000 credits
  • 1,000,000 credits≈ pages a monthLevel 11MLevel 2250kLevel 340k
  • 50 concurrent requests
  • Sticky sessions
  • Priority email support
Choose Growth

Business

$299/mo
$0.075 per 1,000 credits
  • 4,000,000 credits≈ pages a monthLevel 14MLevel 21MLevel 3160k
  • 150 concurrent requests
  • Usage & spend limits per key
  • Shared Slack channel
Choose Business

Scale

$699/mo
$0.058 per 1,000 credits
  • 12,000,000 credits≈ pages a monthLevel 112MLevel 23MLevel 3480k
  • 500 concurrent requests
  • Per-site tuning
  • Dedicated engineer
Choose Scale

Enterprise

From $0.045 per 1,000 credits above 12M. 1,000+ concurrent requests, SLA, dedicated routes, annual contract.

Talk to sales

Which plan fits?

Move the slider to your monthly volume.

Recommended
Start $29

100,000 of 250,000 credits a month

Start free, upgrade later →

What a page costs

We detect the level automatically and bill the one it actually took. You never pick a level up front, and every response tells you what it cost.

LevelCreditsTypical targets
Level 11APIs, news, blogs, most sitesUnlimited transfer
Level 24Marketplaces, classifieds, busy sites500 KB per page included
Level 325The hardest pages500 KB per page included

The fine print, in plain words

  • Failed or timed-out pages cost 0 credits. So do our retries. A failed page means the site still refused after 30 seconds of tries, or we couldn't reach it. A page the site says doesn't exist, such as a 404, isn't delivered, so it costs 0 credits too.
  • A page never costs more than 25 credits. That's under 1 cent pay as you go, before any transfer above 500 KB.
  • Concurrency is how many requests you can have in flight at once. Need more on a smaller plan? Ask us.
  • Above 500 KB per Level 2 or Level 3 page, transfer is $0.50 per GB.
  • Run out mid-month? Top up at your plan's rate +15%, or let auto top-up do it.
  • Unused monthly credits don't roll over. Free credits don't expire.
  • Pay yearly and save 10% on every paid plan.
  • No plan? Pay as you go at $0.30 per 1,000 credits.
  • Cancel any time from the dashboard.
FAQ

Questions, answered

Do I pay for failed pages?

No. We charge credits only for delivered pages. Failed tries, timeouts and our own retries are on us.

How many credits does a page cost?

1 credit at Level 1, 4 at Level 2 and 25 at Level 3. We pick the level automatically and return the cost with every response in X-DD-Credits.

Can my AI agent use DoubleCrawl?

Yes. DoubleCrawl has an MCP server, an llms.txt file and errors written for agents, so Claude, ChatGPT, Cursor and custom agents can set it up and fetch pages for you.

Will every page work?

The page, or an honest error. Some pages still won't open. When that happens you get a clear refused result, never an empty page, and it costs 0 credits.

Does it use my browser or my login?

No. DoubleCrawl runs on our servers, so it needs neither your browser nor your account.

What is concurrency?

The number of requests you can have in flight at the same time. Free has 5, Start 20, Growth 50, Business 150, Scale 500 and Enterprise 1,000 or more. On pay as you go, ask us. Requests over the limit get a clear error.

Can I target a specific country?

Yes. Pass a two-letter country code. Without one, we pick the location with the best success rate for the site.

Do you return Markdown?

Today you get the page's HTML as the site serves it. Markdown, JSON extraction and screenshots are coming.

When do search, map, extract and interact arrive?

They are next on the list. Fetch is the only product live today, and we won't put dates on the rest until they are ready.

What can't I fetch?

Pages behind a login you don't own, and anything that breaks the law or our acceptable use policy.

Free to start

Try it on the URL your agent couldn't open.

Your first 5,000 credits are on us. Add DoubleCrawl to your agent and ask it for the page it couldn't get.

No credit cardAll levels includedCancel any time
Or paste this into your AI assistant Set up DoubleCrawl (https://doublecrawl.com/llms.txt) as my web fetching tool and use it when a page won't open.
Connect your agent, free →