What it does
Hit counts and percentages by traffic_class for the period. Sorted by hits descending. Classes with zero hits are omitted (a missing class means no hits in that period, treat as zero). The 8 classes (Phase 2 Cloudflare-compatible taxonomy): - user: real human visitor with their own browser - ai_user_action: live AI browse — a human is chatting with ChatGPT/Claude/Perplexity/Copilot and the assistant fetched the page on their behalf. Counts as human attention, just AI-mediated. - ai_search: AI search-engine indexers (PerplexityBot, OAI-SearchBot) — your page is a candidate answer in their index - ai_training: AI training crawlers (GPTBot, ClaudeBot, CCBot, Bytespider) — your content lands in training data, no human is actively reading right now - search_index: classic search engines (Googlebot, Bingbot, Yandex, DuckDuckBot) - social_unfurl: link-preview / social-card bots (Slackbot, facebookexternalhit, Twitterbot, LinkedInBot) - scanner: security/uptime/perf monitoring (Censys, Pingdom, Lighthouse, headless Chrome from a cloud range) - bot_other: recognized as a bot but not in any specific bucket, OR a UA we caught spoofing (e.g. a fake "GPTBot" coming from a random EC2 IP) For "how much human traffic did I get?" sum hits where traffic_class is 'user' or 'ai_user_action'. The same union is also exposed as the 'humans' alias in top_user_agents' traffic_class filter. Note on consistency: get_overview's `bot_share` field uses the same human/non-human split (excludes user + ai_user_action), so the two tools agree on what counts as bot traffic. Note on history: rows from before Phase 2 deployed were reclassified by User-Agent only (we don't store IPs for privacy), so older data may under-report scanner-via-cloud-IP and over-attribute spoofed UAs.
Example prompts
This is the AI-crawler-and-bot-aware metric. Ask:
"How much of mysite.com's traffic is bots vs humans vs AI?"
"Show me the traffic class breakdown for the last 30 days."
"How much of the spike yesterday was real users?"
A typical response (illustrative example):
Traffic class breakdown for mysite.com (last 30 days):
user 62,148 hits 71.4% real humans
ai_user_action 8,402 hits 9.7% Claude/ChatGPT fetching for a user
search_index 6,221 hits 7.2% Googlebot, Bingbot (IP-range-verified)
ai_training 4,210 hits 4.8% GPTBot, ClaudeBot, CCBot, etc.
ai_search 1,637 hits 1.9% PerplexityBot, OAI-SearchBot
social_unfurl 1,841 hits 2.1% Slackbot, LinkedInBot, Twitterbot
scanner 947 hits 1.1% uptime, security, headless monitoring
bot_other 618 hits 0.7% recognised bot, no specific bucket
The eight classes are Cloudflare-compatible (their AI Crawl Control taxonomy), so cross-tool comparisons work. Returns a list of { traffic_class, hits, percentage }.
Why this matters:
userplusai_user_action= your real human audience. Sum is what most other analytics tools call "pageviews": they fold both buckets together. We keep them separate because AI-mediated browsing has different attribution characteristics.ai_trainingtells you how aggressively AI training crawlers (GPTBot, ClaudeBot, CCBot) are indexing your content. If they're a meaningful share, your content is in their training pipelines.ai_searchcovers answer-grounding crawlers (PerplexityBot, OAI-SearchBot). Relevant to AI-search visibility planning.search_indexcovers traditional search crawlers, verified against the vendors' published IP ranges (Google, Bing). Anthropic's crawlers, which don't publish ranges the same way, are verified via FCrDNS (reverse-DNS plus forward-DNS) instead. Mis-claimed Googlebot lands inbot_other, not here.scannercovers uptime, security, and headless-browser monitoring. Worth knowing if it's unexpectedly high.
For digging into specific bot UAs, follow up with
top_user_agents
filtered by a class.
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
|
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": "traffic_class_breakdown",
"arguments": {
"site_id": "abc12345"
}
}
}'
Token comes from /settings after you sign up. Replace any required arguments above.
Related tools
engagement_overview: Real reading time + scroll depth from the engagement beacon (fired on pagehide).list_sites: List all sites on the authenticated account.top_bots: Named-bot breakdown: which crawlers fetched the site, by canonical bot name (GPTBot, ClaudeBot, PerplexityBot, Googlebot, ...) with their traffic_class and hit counts.get_timeseries: Time-bucketed metric over a period.get_overview: TL;DR for the period: headline metrics (pageviews, visitors, sessions, bounce rate, avg session duration) plus pageviews_change_pct vs the previous equivalent window, top page, top traffic source, bot share, and top 3 custom events.