Now Available as MCP Tool

Page
Structure MCP

One HTTP call turns any URL into a structured map — headings, sections, forms, links, and metadata. No browser. No JavaScript. Under 2 seconds.

See it in action → How it works
extract structure — preview.aivibehosting.com
$ extract_structure("https://propertieschiangmai.com/about-us/")
 
URL: "https://propertieschiangmai.com/about-us/"
Title: "About Us – Properties Chiang Mai"
Sections: 20
Headings: 25
Forms: 6
Links: 49
Response time: 1.2s
 
// Full heading tree extracted below
├── H1: "About Properties Chiang Mai"
│ ├── H2: "Who We Are"
│ ├── H2: "Why Buy With Us?"
│ │ ├── H3: "Ease Of Communication"
│ │ ├── H3: "Company Values"
│ │ └── H3: "Multi-Agency Colabs"
│ ├── H2: "Messsage Us"
│ └── H2: "Try Our App"

Every structural layer,
instantly mapped

No rendering engine, no DOM traversal, no style computation. Just raw structure — served as clean, readable text.

📑

Heading Hierarchy

Full H1→H4 tree in DOM order. Know exactly how a page is organized — sections, subsections, and their nesting.

🧩

Elementor Widgets

Identifies every Elementor widget type per section — headings, icon-boxes, text-editors, forms, spacers, and more.

📋

Form Detection

All form fields extracted with placeholders, types, and required flags. Know what data a page expects before you scrape.

🔗

Link Inventory

Every link on the page with text + href. Navigation menus, footer links, CTAs — all captured in one pass.

🎨

Icon Classes

All houzez-iconfont and CSS icon classes used on the page. Know which icons a design depends on without inspecting.

📊

Section Metadata

Background colors, inline styles, data-settings, CSS classes, and widget types for every section on the page.

One URL → Structured Data
in under 2 seconds

No browser, no JavaScript execution, no headless Chrome. Just raw HTTP + pattern matching.

Input
URL
Process
HTTP Fetch + Parse
Output
Structured Text

What you get back

Clean, readable structure — not raw HTML or JSON blob. Designed for human review and agent consumption.

H1 About Properties Chiang Mai
H2 Who We Are
H2 Why Buy With Us?
H3 Ease Of Communication
H3 Company Values
H3 Multi-Agency Colabs
H2 What we do for buyers
H3 Shortlisted Recommendations
H2 Property types we cover
H2 Where we operate
H2 Let’s find your place
H2 What our customers saying
FORM Contact Info
text "First name" *
text "Last name" *
email "Email address" *
tel "Phone number (+66 946381920)" *
number "Min. bedrooms"
number "Your budget (THB)"
textarea "Tell us a bit about your needs"
BTN Submit
└── 8 fields · 5 required

Built for speed,
designed for agents

Zero browser dependencies. Pure Node.js HTTP + pattern matching. Runs as a stdio MCP server.

Avg Response Time
< 2 seconds
📦
Dependencies
Zero (stdlib only)
📐
Max Page Size
2 MB
🔌
Protocol
MCP stdio
📄
Output Format
Readable text
🔄
Redirects
Auto-follows

When to reach for this tool

The style-inliner gives you pixel-perfect CSS. This one gives you the blueprint.

1

Design Replication

Before building a page, understand its section structure, heading hierarchy, and form fields.

2

Content Audit

Map out every heading, link, and form on a page in seconds — no manual scrolling.

3

WordPress Analysis

Identify Elementor widgets, section settings, and icon dependencies without logging into WP admin.

4

Agent Pre-flight

Before an agent edits a page, load its structure so it knows exactly what exists and where.

Two MCP tools,
one pipeline

Use together for full page replication: structure first, then styles.

Featurepage-structure MCPstyle-inliner MCP
Speed~1-2s~1-2s (90 properties)
Browser required❌ No✅ Headless Chrome
CSS computed✅ Full inline
Heading tree✅ Full hierarchy
Form fields✅ With placeholders
Max page size2MB~500KB (before timeout)
Use caseBlueprint / structurePixel-perfect export
Get started

Ready to use it?

Already registered in this Hermes session. Just reload MCP and call extract_structure(url)

/reload-mcp then call the tool