Web Anatomy MCP

The landing page reference your AI agent is missing

Web Anatomy MCP connects your AI agent to 4,000+ scored sections and 700+ full pages from 750+ real companies, so what it builds starts from what already works.

Included in Pro · 750+ real companies · Claude · Cursor · Codex

Get started Read the docs

Your agent is guessing. It shouldn't have to.

Most AI pages are averaged from training data. Web Anatomy grounds your agent in what the best websites actually shipped.

Without Web Anatomy

Your agent pattern-matches from training data
Generic three-tier pricing, 'Get started' CTAs
Galleries show pretty pages, never what works

> design our pricing page

// generic, averaged from training data

With Web Anatomy

Ask in plain English: 'design our pricing page'
Your agent calls a named move from a real company
It ships what performed, with real screenshots

Design our pricing page.

Based on best practices for your industry and ICP, it pulls the pricing cards that performed:

Linear

Highlighted "Business" card anchors the recommended plan.

+ Raycast, Clay

Connect to Claude, Cursor, or any MCP-compatible client

Connect MCP

Why use it

From guesswork to evidence

Grounded in real pages

Every suggestion points to a real, high-performing website your agent can show you, so you trust the recommendation.

Skip the blank page

Find proven hero, pricing, CTA, and FAQ patterns by industry in seconds, instead of starting from an empty section.

Inside the agent you already use

No new app to learn. It works in Claude, Cursor, Codex, and any agent that speaks MCP, right where you already build.

Outputs your team can ship

Turn the findings into a clean report or a prioritized fix list you can act on or hand to whoever owns the code.

What your agent can do

Four jobs, done with real evidence

Use the MCP when your agent needs real website evidence before it recommends, edits, or writes.

Find proven section examples

Ask for hero, pricing, FAQ, comparison, or signup examples filtered by industry and locale.

Example prompt

Find AI hero examples with strong social proof.

Improve a page section

Paste your section or screenshot and ask your agent to compare it against stronger examples before editing copy or layout.

Example prompt

Improve this pricing table using Web Anatomy examples.

Benchmark a URL or screenshot

Give your agent a live page or screenshot and ask for gaps, stronger references, and prioritized fixes.

Example prompt

Benchmark our homepage against top AI landing pages.

Turn references into a report

Ask for the output in chat, a Markdown file, or an HTML report so your team can act on it.

Example prompt

Create a short .md report with examples and fixes.

Available where you work

Connect it to the agent you already use

Add Web Anatomy to your coding agent in a couple of minutes. The full per-IDE guides live in the docs.

Claude Code

One command at user scope. The recommended setup.

Setup guide

Cursor

Add the server to your ~/.cursor/mcp.json.

Setup guide

Windsurf, VS Code, Codex, Gemini CLI, and any other MCP client are covered in the documentation. Read the documentation.

FAQ

Questions, answered

The short version is here. The full detail lives in the docs. Read the docs.

Where do I get my token?

In the MCP dashboard, as soon as your Pro subscription is active. There is no review queue. The install prompt is customized with that one-time token.

Where should the token be stored?

Keep it in ignored local config, such as an env var or $HOME/.webanatomy/webanatomy_mcp_token. Do not commit it.

What data can the MCP return?

It returns public-safe benchmark sections, filters, and selected section details. It does not return raw scores, marker coordinates, service-role access, or internal database fields.

Which agents does it work with?

Claude, Cursor, Codex, or any coding agent that can configure an MCP server through mcp-remote. The dashboard gives you the exact command for yours.

What if I already use Mobbin or Lazyweb?

Keep using visual libraries for browsing. Web Anatomy is for grounding your coding agent in benchmark-backed examples it can call while working.

Get started

Give your agent real landing-page evidence

Connect Web Anatomy to the agent you already use and it builds from real pages instead of training-data averages. Included in Pro.

Connect MCP Read the docs