Analyze website (`adsap_analyze_website`)

Platform: Meta · Read or write: Read · Plan: All plans · Consumes a task: No · Preview supported: No

What it does

Fetches a website URL and reads what it can find. It extracts business context, tracking scripts (Meta Pixel, GTM, GA4, TikTok), product and pricing signals, value proposition, social proof and landing page quality. Adsap stores the result, so later conversations can reuse it. Use it as the first step when setting up a new account.

When to use it

Use it at the start of account setup, before saving a plan with adsap_manage_onboarding_plan.
Pass the full address with https://. A url without a protocol is refused with INVALID_INPUT.
It reads the one page you pass. subpage_analyses comes back empty, so call it again for another page.
It reads the page HTML. When it finds a Google Tag Manager container, it also reads the container script for pixel IDs.
It finds tags on the page. It does not check that events arrive at Meta. For that, use adsap_get_pixel_stats.
A site that blocks automated requests, or is down, returns FETCH_ERROR.

Worked example

You ask

“Analyze https://www.example.com and tell me what they sell and which tracking is installed.”

The assistant calls `adsap_analyze_website`


{
  "url": "https://www.example.com"
}

Adsap returns

The field names are the ones Adsap returns. The values are examples.


{
  "domain": "example.com",
  "url": "https://www.example.com",
  "tracking": {
    "meta_pixel_ids": ["123456789012345"],
    "gtm_ids": [],
    "ga4_ids": ["G-ABCDE12345"],
    "tiktok_pixel": false,
    "other_scripts": []
  },
  "business_context": {
    "name": "Example Home",
    "description": "Furniture and lighting for small spaces.",
    "industry_signals": ["lighting", "furniture"],
    "platform": "shopify"
  },
  "pricing": {
    "price_range": { "min": 29, "max": 89, "currency": "USD" },
    "model": "one_time"
  },
  "landing_quality": {
    "has_mobile_viewport": true,
    "has_cta_above_fold": true,
    "has_form": true
  },
  "cached": false,
  "analyzed_at": "2026-09-18T09:30:00.000Z",
  "human_readable_summary": "Example Home is a shopify-based website. Industry signals: lighting, furniture. Products range $29-$89. Meta Pixel detected (ID: 123456789012345). GA4 tracking present. Mobile-optimized. Clear CTA above fold."
}

How to read it

human_readable_summary is the short version. tracking lists the IDs found on the page: meta_pixel_ids, gtm_ids and ga4_ids. An empty meta_pixel_ids means no Meta Pixel was found in the HTML or in the Google Tag Manager container. pricing.price_range is null when no prices are found. landing_quality holds quick checks, such as a mobile viewport tag and a call to action near the top.

The full response also has value_proposition (page title, meta description and headings) and social_proof (review widgets, testimonials, trust badges and FAQ items). business_context.product_schema lists products found in structured data. A usual next step is adsap_get_account_health, then saving a plan with adsap_manage_onboarding_plan.

Parameters

Descriptions are shortened from the tool schema. Your assistant sees the full text.

Name	Type	Required	Description
`url`	string	Yes	Website URL to analyze. Must include protocol (https://).

Example prompts

“Analyze example.com and tell me what the business sells and which tracking scripts are installed.”
“Look at our landing page and tell me if the Meta Pixel is present.”
“Read my website and summarize the value proposition and social proof you find.”

adsap_manage_onboarding_plan: Create, read, update, or delete a structured onboarding plan for a Meta ad account.
adsap_ping: Verify Adsap MCP server connectivity and API key.

Guide

Read AI Copilot setup for the workflow around this tool, and the Tool reference for every tool.

The Meta Ads MCP server page shows how to connect Meta Ads to Claude, ChatGPT or Perplexity.

Analyze website (adsap_analyze_website)