What it does

Most-viewed URL paths. Counts both direct browser visits and AI-mediated human browsing (ai_user_action) — see traffic_class_breakdown if you need to separate them. With conversion_event a row counts everyone who viewed the page at any point in the period, wherever they entered; for "which landing pages convert" use top_entry_pages.

Example prompts

Ask:

"What are my top pages on mysite.com last 30 days?"
"Top 20 pages for example.com this week."
"Which URLs are getting the most traffic right now?"

A typical response, formatted by Claude:

Top pages for mysite.com (last 30 days):

  1. /                            14,232 views
  2. /pricing                      8,914 views
  3. /blog/llms-txt-explained      4,847 views
  4. /docs                         3,210 views
  5. /vs/google-analytics          2,891 views
  6. /blog/claude-mcp-setup        2,447 views
  7. /vs/plausible                 2,108 views
  8. /de/blog/mcp-server-anleitung 1,963 views
  9. /docs/setup                   1,442 views
 10. /privacy                      1,287 views

Returns an array of { path, pageviews } objects. Counts include both direct browser visits and AI-mediated human browsing (ai_user_action, e.g. Claude fetching a page on a user's behalf). If you need to separate them, follow up with traffic_class_breakdown.

For long-tail SEO investigation you can stack this with compare_periods to identify pages that grew or fell sharply between periods.

Arguments

Name Type Required Description / Default
site_id string required Site identifier from list_sites (8-character base32, e.g. 'wjxayhdd').
period string optional Time window. Keywords: today, yesterday, last_7_days, last_30_days, last_90_days, last_12_months. Or a custom date range YYYY-MM-DD..YYYY-MM-DD (inclusive).
default: last_7_days
limit integer optional Maximum number of rows to return. Capped at 1000 server-side.
default: 10
conversion_event string optional Optional custom event name (case-sensitive, from list_events) to treat as the conversion. Each row then gains conversion_base (units in that row), converted (how many of them fired the event anywhere in the period) and conversion_rate (ratio 0–1: 0.05 means 5%; null when no unit is attributed to the row: it has no browser sessions/visitors at all, e.g. purely server-ingested traffic, or — on privacy_mode=all sites in top_referrers/top_sources/top_entry_pages — the row was never any visitor's first entry in the period, even though it has sessions). The response gains a site-wide `conversion` block: conversion_base (units in the period), converted (how many fired the event), conversion_rate (ratio 0–1: 0.05 means 5%), `unit` and a `note` to relay. Use it to compare conversion rates between rows — absolute counts alone favour whatever row has the most traffic. The unit depends on the site's privacy_mode: 'session' on strict and balanced sites (no identity survives UTC midnight there, so only conversions within one visit count), 'visitor' on privacy_mode=all sites (first-party cookie, so a visitor who arrives Monday and converts Thursday counts as converted, if both days are inside the period). The auto-tracked 'pageview' and 'engagement' are rejected — pick one of the site's own events.

How to call it directly

If you're integrating from your own code rather than a chat client, this is the JSON-RPC payload:

curl -X POST https://mcp-analytics.com/mcp \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "top_pages",
    "arguments": {
      "site_id": "abc12345"
    }
  }
}'

Token comes from /settings after you sign up. Replace any required arguments above.

Related tools