Grounded in real pages
Every suggestion points to a real, high-performing website your agent can show you, so you trust the recommendation.
Web Anatomy MCP
Your AI agent, grounded in landing pages that actually convert
Web Anatomy connects your coding agent to a live benchmark library of real, high-performing websites. It finds proven section patterns, benchmarks your page, and recommends fixes from evidence, not guesswork.
Free to start · Private beta MCP · Claude · Cursor · Codex
Why use it
From guesswork to evidence
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.
01
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.
02
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.
03
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.
04
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 guideCursor
Add the server to your ~/.cursor/mcp.json.
Setup guideWindsurf, VS Code, Codex, Gemini CLI, and any other MCP client are covered in the documentation. Read the documentation.
Where do I get my token?
After approval, generate it in the MCP dashboard. 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?
Use the copied prompt with Codex, Claude, Cursor, or any coding agent that can install skills and configure an MCP server through mcp-remote.
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.
Start free
Give your agent real landing-page evidence
Install the free skills in one command, then connect the private-beta MCP when you want live examples and URL benchmarks.