Copied!

Reverse-Engineer Any Website With Claude

Analyze animations, WebGL, shaders.
Get the code. Rebuild anything.

Start Analyzing
↓ Scroll to explore

How does Enrichr take
a site apart?

+ 3,000 elements parsed

We read the rendered DOM.

Not the source you wish had shipped — the DOM after JavaScript ran and the page settled. Every node, every applied rule, every computed value.

+ 5,000 keyframes traced

We capture the motion, the part a screenshot always loses.

Keyframes, easings, durations, scroll triggers, hover and focus states — recorded as values you can rebuild from.

+ 10 analysis layers

You never start from a blank file.
We hand it straight to Claude.

Design tokens, a used-CSS sheet, responsive deltas and a rebuild brief — delivered over MCP, ready to build against.

Reverse-Engineer Any Website
Reverse-Engineer Any Website

Three steps
to get started

Step 1 — Copy your API key
Endpoint: https://enrichr-production-0632.up.railway.app/mcp
API Key:   enrichr_your-key-here
Step 2 — Add to Claude
Settings → Connectors → Add custom connector

Name: Enrichr
URL:  https://enrichr-production-0632.up.railway.app/mcp/k/enrichr_your-key-here

That's both fields — your key is in the URL, so
there's no header to configure.

On step 2, choose "No sign-in". Enrichr uses this
key, not OAuth.

Claude Code:
claude mcp add --transport http enrichr \
  https://enrichr-production-0632.up.railway.app/mcp \
  --header "X-API-Key: enrichr_your-key-here"
Step 3 — Start analyzing
In Claude:
"Reverse-engineer https://example.com"

That's it. Start analyzing.

What Enrichr Detects

Layer 2

Animations

  • GSAP & ScrollTrigger
  • Framer Motion
  • Lenis smooth scroll
  • Exact timings & easing curves
Layer 3

WebGL & 3D

  • Three.js & Babylon.js
  • Custom GLSL shaders + complexity ratings
  • 3D models (GLB, GLTF, OBJ)
  • Particle systems
Soon

Coming Next

  • Post-processing chains
  • More animation libraries
  • Performance metrics

What a fetch cannot see

A model without a browser gets one thing: the bytes the server returns. Here is the same page measured both ways — a three.js demo whose entire content is built at runtime, in GPU memory.

Measured on threejs.orgPlain fetchEnrichr
HTML returned4,121 bytes47,092 rendered
WebGL shaders032
Draw calls per frame079
3D scene meshes072
Network requests124
CSS actually appliedunknowable2% of shipped

And on a production marketing site — stripe.com, which is server-rendered, so the markup gap is small and the capability gap is not:

Measured on stripe.comPlain fetchEnrichr
Design tokens0435
Hover / focus / active states037
Responsive style changes0180 across 4 viewports
API endpoints discovered027
Text read off the pixels0139 words
CSS actually appliedunknowable53% of shipped

Then download the whole thing: rendered DOM, every asset pulled local, the CSS that actually applied, and the analysis — a folder that opens offline with the network disconnected.

Simple credit pricing

One credit is one ordinary extraction. A deep capture costs more because it holds a real browser for longer — a full rebuild brief is 5, a design-token read is 1, checking vision availability is free.

Free

$0
  • 25 credits / month
  • Every extraction tool
  • 1 concurrent run
Start free

Starter

$19/mo
  • 500 credits / month
  • Source-map recovery
  • 2 concurrent runs
Choose Starter

Scale

$299/mo
  • 15,000 credits / month
  • 15 concurrent runs
  • Private deployment help
Choose Scale

Need more for one busy month? Buy credit packs from your account — 250 for $12, 1,000 for $40, 5,000 for $175. Purchased credits never expire.

Got
questions?

  • No. You ask Claude in plain English — "reverse-engineer this site" — and Enrichr does the browser automation and extraction. Claude reads the results and explains them back to you.

  • A fetch gets the bytes the server returned before any JavaScript ran. Enrichr renders the page in a real browser first, so it sees what actually got applied — animations, WebGL, hover states, the CSS that survived, all of it. See the Proof section above for real numbers.

  • Anything a real browser can render — React, Vue, and Next apps, Three.js and WebGL scenes, GSAP-heavy sites, pages behind a Cloudflare challenge. If it loads in Chrome, Enrichr can capture it.

  • One credit is one ordinary extraction. Deeper captures cost more because they hold a real browser open longer — a full rebuild brief is 5 credits, a design-token read is 1, checking vision availability is free. Full breakdown in the Pricing section.

  • We store a hash of your key, never the plaintext — it's shown once, at creation. Every extraction runs in an isolated browser instance, and nothing about the sites you analyze is shared with anyone beyond the Claude conversation that requested it.

  • Yes — run Enrichr locally as a stdio MCP server and there's no API key or account involved at all. Accounts and credits only come into play for the hosted version.