Design API and MCP server for AI agents

Give any website's design to AI agents like ChatGPT, Claude, Claude Code, Grok Bot, Muse, OpenAI dots, Codex, Cursor, OpenClaw and Hermes Agent, through one API or MCP server

Connect once and your agent can read any live page: its code, colors, fonts, logos and assets. It builds with what is really there.

Try it on any site. No signup.

Start for $0

300 free credits every month. No credit card.

Tell your agent what you want

What you can get

Everything on a page, from one URL

Under the hood

The hard parts, handled

Modern sites build their design with JavaScript, layered stylesheets and lazy loading. You send a URL. We deal with the rest.

  • Runs in a real browser

    Every code call loads the page in Chrome, so sites built with JavaScript come back the way they look.

  • Re-renders when it has to

    Other calls read the HTML first. If it comes back empty or the site blocks us, we load it in a browser for you, at no extra cost.

  • Resolves the CSS

    Stylesheets, overrides and variables are worked out for you, so you get the values the page really shows.

  • Keeps hover and mobile styles

    HTML, Elementor and Shopify output carry the section's hover states and breakpoints.

  • Brings the real fonts

    The font files a section uses come with it, so the type matches the original.

  • Bills only for results

    Failed calls are free, and a repeat call within 24 hours costs 0 credits instead of 10.

What you can do with it

Four things people do on day one.

Power your builds
with AI and automation

Call it from your code, hand it to your AI agent, or run it in n8n.

For developers

Call it from your code

One GET with your key, typed JSON back. Any language, nothing to install.

AI agents

Ask your AI agent

It calls MiroMiro as a tool whenever it needs a site’s design, and builds with the real thing.

ChatGPTClaudeCursorCodexClaude CodeMuse
Automaten8n verified

Automate everything

MiroMiro is live on the Apify Store: pay per result, schedule runs, chain it with other tools. Our n8n node is verified by n8n, with ready-made templates for Elementor, Shopify, code and brand kits. Make, Zapier or any tool that sends an HTTP request can call the API too.

Pay for what you extract

Start with all endpoints and 300 free credits - no card. Failed calls are never billed, cached repeats are free, and you can cancel anytime - no questions asked.

Developer

Most chosen

For your first product on the API.

€16/month

Billed €190/year

€0.03 per section as code

5,000 credits / month Credits are weighted by endpoint - from 1 for an asset scrape up to 10 for a full URL-to-code call. Failed calls are never charged.

60 requests / minute Burst rate limit per API key. Requests over it return a 429 - wait a moment and retry.

Free cached repeat calls Save credits: repeat calls to a URL you've already extracted are served from cache and cost 0 credits.

JS rendering +5 cr / call Client-rendered sites (React, Next) are re-read in a real browser automatically, at no extra cost. Add render=true to any call to force it: flat +5 credits, only when you use it. Rendered calls can also return a screenshot of the page (viewport or full-page) at no extra credits - add screenshot=true.

  • Rebuild 500 sections as code
  • Look up 500 company brands
  • Extract 5K image or SVG lists
  • White label: use it in a product you sell
  • All 9 endpoints + MCP connector
  • Elementor templates + Shopify sections
  • Usage dashboard + email support

Growth

For products in production with real traffic.

€66/month

Billed €790/year

€0.02 per section as code

30,000 credits / month Credits are weighted by endpoint - from 1 for an asset scrape up to 10 for a full URL-to-code call. Failed calls are never charged.

120 requests / minute Burst rate limit per API key. Requests over it return a 429 - wait a moment and retry.

Free cached repeat calls Save credits: repeat calls to a URL you've already extracted are served from cache and cost 0 credits.

JS rendering +5 cr / call Client-rendered sites (React, Next) are re-read in a real browser automatically, at no extra cost. Add render=true to any call to force it: flat +5 credits, only when you use it. Rendered calls can also return a screenshot of the page (viewport or full-page) at no extra credits - add screenshot=true.

  • Rebuild 3K sections as code
  • Look up 3K company brands
  • Extract 30K image or SVG lists
  • Everything in Developer
  • Priority support
  • Invoice billing and VAT receipts
  • DPA on request

Scale

For platforms extracting across many customer sites.

€166/month

Billed €1990/year

€0.01 per section as code

200,000 credits / month Credits are weighted by endpoint - from 1 for an asset scrape up to 10 for a full URL-to-code call. Failed calls are never charged.

300 requests / minute Burst rate limit per API key. Requests over it return a 429 - wait a moment and retry.

Free cached repeat calls Save credits: repeat calls to a URL you've already extracted are served from cache and cost 0 credits.

JS rendering +5 cr / call Client-rendered sites (React, Next) are re-read in a real browser automatically, at no extra cost. Add render=true to any call to force it: flat +5 credits, only when you use it. Rendered calls can also return a screenshot of the page (viewport or full-page) at no extra credits - add screenshot=true.

  • Rebuild 20K sections as code
  • Look up 20K company brands
  • Extract 200K image or SVG lists
  • Everything in Growth
  • Lowest price per call
  • Priority support
  • Invoice billing and VAT receipts
  • DPA on request

Custom

For volume that outgrows a plan, on your paperwork.

Custom

Volume pricing

Unlimited credits Credits are weighted by endpoint - from 1 for an asset scrape up to 10 for a full URL-to-code call. Failed calls are never charged.

Negotiated volume & rate limits

Free cached repeat calls Save credits: repeat calls to a URL you've already extracted are served from cache and cost 0 credits.

JS rendering +5 cr / call Client-rendered sites (React, Next) are re-read in a real browser automatically, at no extra cost. Add render=true to any call to force it: flat +5 credits, only when you use it. Rendered calls can also return a screenshot of the page (viewport or full-page) at no extra credits - add screenshot=true.

  • Rebuild Unlimited sections as code
  • Look up Unlimited company brands
  • Extract Unlimited image or SVG lists
  • Everything in Scale
  • Volume pricing, no per-plan cap
  • Rate limits set to your workload
  • Annual contract and PO or bank transfer
  • DPA, security review and uptime SLA

Free plan: 300 credits a month, no card, to try the API and build. A product you sell needs a paid plan. Prices don't include VAT. Need more credits or a different plan?

30-day money-back guaranteePowered by Stripe

Questions before you start

What does the MiroMiro API do?

You give it the URL of any public website and it gives back that site's design: a section as working code (Tailwind, HTML, React, Vue, or an Elementor or Shopify file), the brand colors, fonts and logo, the full set of design tokens, and every image, SVG icon, font file and Lottie animation on the page. Your AI agent can call it as a tool, or you call it from your own code.

What do I get for free?

An API key with 300 credits every month, every endpoint, and the MCP server - no credit card. The playground needs no signup at all. Upgrade when you need more volume, not to get started.

How do I connect it to ChatGPT, Claude or my coding agent?

In ChatGPT or Claude, add MiroMiro as a connector and sign in - there is no key to copy, and each app has a step-by-step page above. In a coding agent like Cursor, Claude Code or Codex, paste one instruction and the agent reads our docs and integrates itself, or install the MCP server (npx miromiro-mcp) so it gets the tools natively and reaches for them on its own.

Does it work on sites built with JavaScript?

Yes. Every code call loads the page in a real Chrome browser. The other calls read the HTML first and, if it comes back empty or the site blocks the request, load it in a browser automatically at no extra cost. For images or animations that only appear when you scroll, pass render=true (+5 credits).

What counts as a credit?

Credits are weighted by how much work an endpoint does - from 1 credit for an asset scrape up to 10 for a full URL-to-code extraction, which resolves the page's entire CSS cascade. Failed and blocked requests are never billed, and a cached repeat call is free - the meter only moves on fresh, successful work.

What happens when I run out of credits?

On the free plan, calls return a 429 with a clear message until your credits reset at the start of the next month - or you upgrade, which takes effect immediately and keeps the same key. Paid plans keep working: extra credits are billed at your plan's per-1,000 overage rate on a separate invoice, capped at one extra month of credits so a runaway script can never produce an unbounded bill. Prefer a hard stop? Switch overage billing off in your console and your key stops at the quota instead - nothing extra is ever billed.

How is this different from a web scraper?

Scrapers return HTML or markdown - text soup you still have to parse. MiroMiro reads the page as design: typed design tokens, resolved asset URLs, real font files, and inline SVG code. One call returns structured design data, not a document.

Can I turn a website section into an Elementor template or a Shopify section?

Yes. Call the code endpoint with framework=elementor and you get a template file to import in WordPress under Templates, Saved Templates. With framework=shopify you get a section file for your theme. Both arrive as one styled HTML block that you edit as code, not as native widgets, with the responsive and hover styles of the original. The same call returns Tailwind, plain HTML and CSS, React or Vue when you want code to paste instead.

What do you do with the URLs I send and the pages you fetch?

We fetch only public pages - no logins, no cookies, no authenticated sessions. The raw page we fetch is processed in memory and discarded - it is never stored. The extracted result - the same JSON you get back - is cached for 24 hours so a repeat call by anyone is instant and free, then it's deleted; pass fresh=true when you need a live re-extraction. We do record which URL each of your calls hit, because that's what powers the usage history in your dashboard; those rows are row-level-security scoped to your account, so nobody else can read them. Your API key is stored only as a SHA-256 hash - we cannot recover the raw secret, which is why it's shown exactly once.

Same engine as the extension - 20,000+ developers, 4.5 on the Chrome Web Store Live status & uptime Docs

Give your agent the real design of any website

Its code, colors, fonts, logos and assets, from one URL. Free to start.

Get your free API key

300 free credits every month. No credit card.

Or read the docs first