What it does

Top User-Agent strings with their traffic_class. Default analytics queries hide everything except real visitors; this tool surfaces the rest so you can see who is actually fetching the site. Pass traffic_class to filter to one bucket. 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) The `humans` filter alias expands to (user, ai_user_action) — useful for "real human attention including AI-mediated".

Example prompts

Ask:

"Which bots are hitting mysite.com? Show me the top 20 user agents."
"Show me only ai_crawler user agents for the last 7 days."
"What's the user-agent breakdown for unverified_bot traffic?"

A typical response (filtered to ai_crawler):

Top user agents, ai_crawler class (last 30 days):

  Mozilla/5.0 (compatible; GPTBot/1.2; +https://openai.com/gptbot)
                                                      2,847 hits
  Mozilla/5.0 (compatible; ClaudeBot/1.0; +claudebot@anthropic.com)
                                                      1,612 hits
  PerplexityBot/1.0 (+https://www.perplexity.ai/bot)
                                                        802 hits
  Mozilla/5.0 (compatible; OAI-SearchBot/1.0; +https://openai.com/searchbot)
                                                        412 hits
  Mozilla/5.0 (compatible; CCBot/2.0; +https://commoncrawl.org/...)
                                                        148 hits
  Anthropic/Claude-Web (+https://www.anthropic.com/claude/web)
                                                         92 hits
  Mozilla/5.0 (compatible; Bytespider; +https://www.bytedance.com/spider)
                                                         71 hits
  Mozilla/5.0 (compatible; Applebot-Extended/1.0; +http://www.apple.com/go/applebot)
                                                         48 hits

Default analytics queries hide everything except the user traffic class. This tool surfaces the rest. Pass traffic_class to filter to one bucket (user, ai_user_action, ai_crawler, verified_search_bot, unverified_bot, cloud_egress, headless_browser, unknown), or omit it to see everything.

One of the more popular tools. AI crawler activity changed substantially through 2025 and 2026, and most analytics products silently filter it. Seeing the actual UAs lets you decide whether to Allow: or Disallow: them in your robots.txt, and whether AI crawler hits are a meaningful share of your origin load.

Common follow-up: cross-reference unfamiliar UAs against Cloudflare's AI crawler taxonomy or our own AI crawler index.

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 user-agent rows to return. Capped at 1000 server-side.
default: 25
traffic_class string
enum: user, ai_user_action, ai_search, ai_training, search_index, social_unfurl, scanner, bot_other, humans		 optional Optional filter to a single class. Pass 'humans' as an alias for the union (user, ai_user_action) to see real human attention including AI-mediated browsing.

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_user_agents",
    "arguments": {
      "site_id": "abc12345"
    }
  }
}'

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

Related tools