Haunt API MCP Server
AI驱动的网页数据提取MCP服务器——通过自然语言提示从任何网站提取结构化JSON数据。
文档
Haunt API · Web extraction API for AI agents
HAUNT
**
loading…
How it works Use cases Pricing Docs Get free key
Web extraction API for AI agents
The easiest way to get data off the web.
Haunt reads permitted public pages and hands back structured JSON or clean Markdown. No scraping code, no cleanup.
Get a free key Try the live demo
REST & MCP1,000 free creditsNo credit cardZero retention by default
GET /v1/demo/extract · hauntapi.com homepage
**live
Try the demo for free.
Scan ▸
**loading
no trace left
fetch · confidence · ready
scroll**
Pricing pagesCompany sitesDirectoriesNews & articlesAI agentsRAG pipelinesLead enrichmentCompetitor monitors Pricing pagesCompany sitesDirectoriesNews & articlesAI agentsRAG pipelinesLead enrichmentCompetitor monitors
The shift
Stop copying web
data by hand.
Before Haunt
-
Open pages, hunt for fields, paste into a sheet, and still miss things.
-
Brittle scrapers shatter every time a layout shifts.
-
Other tools fake success on blocked pages and hand you garbage.
-
You inherit a pile of stored page content you never wanted to hold.
With Haunt
-
A pricing page becomes a clean list of plans, prices, limits and features.
-
Need page text for an agent or RAG pipeline? Ask for Markdown instead.
-
One endpoint handles fetch, JavaScript render, and extraction.
-
Blocked or login-only? Haunt says so, and never invents data.
-
Page content, prompts and results are not retained by default.
How it works
Three moves,
no guesswork.
Try the demo, grab a free key to test a page of your own, then connect Haunt to your app or AI agent.
01
Run the live demo
See structured JSON and a confidence trace before you hand over an email. No signup, no key.
02
Claim a free key
Get 1,000 free credits and a ready-to-run curl command pointed at your own URL.
03
Build the integration
Switch between REST, MCP or the SDK and start consuming clean data in your app or agent.
Use cases
Pick your lane.
Most teams start with one concrete extraction, then add the use cases that are actually theirs.
[
Catch price changes faster
Watch a lot of changing pages and get back the fields you can trust, every run. Pricing monitor](http://hauntapi.com/use-cases/extract-pricing-table-from-website) [
Summarise a company fast
Company summaries, metadata and competitor context pulled from public pages. Company extraction](http://hauntapi.com/use-cases/turn-web-page-into-json-api) [
Give your AI cleaner facts
Feed agents reliable website facts as structured JSON or Markdown instead of raw HTML. AI agent path](http://hauntapi.com/use-cases/ai-agent-web-extraction)
No fake magic
It saves time because it tells the truth.
Bad extraction tools waste your time by pretending blocked pages worked. Haunt is built to fail clearly when a page can't support the answer.
-
Works on normal public pages: company sites, pricing pages, docs, articles and directories.
-
Renders many JavaScript pages. Heavy app shells, login walls and verification pages can still fail, and Haunt says so clearly.
-
Returns a clear error when a page is blocked, empty or login-only.
-
Never invents data just to look successful.
Pricing
Start free.
Pay when it's useful.
Simple monthly credits. Failed extractions don't burn credits. No surprise overages.
Freestart here £0*/mo*1,000 credits/month
Enough to prove the first real extraction before you spend anything. Create free key
Starterpopular £19*/mo*10,000 credits/month
For small recurring jobs on reachable public pages. Unlocks scripted browser steps (js_scenario). Choose Starter
Progrow £49*/mo*30,000 credits · bring-your-own headers (beta)
More volume plus authorised headers/cookies for pages you can access. Choose Pro
Scalebatch £99*/mo*80,000 credits · batch + bring-your-own (beta)
Higher volume, batch workflows, same honest failure behaviour. Choose Scale
Start free
Get a free key. Run one command.
No credit card. Free gives 1,000 credits each month. The key appears once, then Haunt gives you a ready-to-copy curl command for your first real extraction.
Haunt does not retain page content, prompts, or extracted results by default. It keeps only the metadata needed for billing, rate limits, abuse prevention and reliability.
Get a free key
No card. Password is only for key regeneration and account management later.
Save this key. It is shown once and cannot be recovered later.
``Copy key
curl commandCopy
Your curl command appears here after signup.
Need Windows quoting?
Windows PowerShellCopy
PowerShell command appears here after signup.
Windows cmd.exeCopy
cmd.exe command appears here after signup.
Expected response: {"success": true, "data": {...}, "trace": {"fetch": {...}, "extraction": {...}, "confidence": 0.92}}
Lost your key? Regenerate it from your account.
Short answers
Questions normal
humans ask.
What does Haunt do?
It extracts useful fields from public web pages as structured JSON, or returns clean Markdown when your agent or RAG pipeline needs page text.
Can I try it without signing up?
Yes. Try the demo above first. Create a key only when you want to test your own URL.
What if the page is blocked?
Haunt detects many CAPTCHA and human-verification blocks and returns a clear error like captcha_required. It does not solve CAPTCHAs or bypass login walls.
How do credits work?
Simple monthly plans based on credits. Failed extractions do not burn credits. No automatic overages. Simple pages usually use 1 credit, normal structured extraction 2, browser-rendered pages 4, and heavy pages 8. Very large pages add 1 credit per ~10,000 tokens of page content (up to 3 extra), so a big page costs a little more than a small one.
Can developers still use MCP or REST?
Yes. REST supports response_format: "markdown", and the MCP package exposes extract_markdown for agent workflows.
Ready when you are
Haunt your first page
in the next five minutes.
Run the demo, get a free key, make one real extraction. No credit card, nothing to install.
Get a free key Try the live demo
Haunt API. Privacy-first JSON and Markdown web extraction for agents and developers. DocsAccountContactPrivacyTermsSecurity