Trust & Traffic Transparency

Every number on this page comes from our production database. No vanity metrics, no cherry-picked screenshots. Here's what's in the catalog, how people use it, and which AI systems and crawlers actually read it.

The catalog

All-time totals across every listed MCP server.

22,577
MCP servers listed
56
Categories covered
92,984
Callable tools indexed
77
Verified listings

How people use it

All-time engagement, summed across every listing page.

13,028
Listing views
135
Install configs copied
75
Upvotes cast

Tool Introspection & Sandbox Verification

How we inspect, parse, and verify executable tool schemas across the directory.

Live MCP Handshakes
715 servers
Verified via live tools/list protocol handshakes against hosted endpoints.
README Structured Parsing
6,874 servers
Extracted from repo documentation for stdio/CLI packages where no HTTP endpoint exists.
Sandbox Verification
29.8% pass rate
2,046 stdio packages isolated and tested in automated execution sandboxes (avg latency: 7.3s).

Catalog Quality Spectrum & Ecosystem Signals

Deterministic quality tiering (0–100) and repository health signals across all active listings.

Listing Quality Tier Distribution (22,577 total active servers):
Excellent: 20 (<0.1%)
Great: 161 (0.7%)
Good: 5,253 (23.3%)
Fair: 14,733 (65.3%)
Emerging: 2,410 (10.7%)
Active Codebases (Last 30 Days)
9,100 listings
Repositories with active commits or pushes measured by automated health checks.

Traffic over the last 30 days

Total requests to our API vs. the subset that came from a named AI assistant. Hover or focus the chart for exact daily numbers.

010K20KAug 23Sep 21
  • AI assistants
  • Total requests

Share of AI Traffic

Market share among AI assistants and LLM crawlers hit over the last 30 days (17,183 total requests).

  • ClaudeBot (Anthropic crawler)98.6% of AI traffic16.9K
  • Gemini / Google1.1% of AI traffic181
  • Jackalope0.2% of AI traffic42
  • Claude / Anthropic<0.1% of AI traffic11
  • ChatGPT / OpenAI<0.1% of AI traffic10
  • Perplexity AI<0.1% of AI traffic2

Who's reading the API

85,934 requests from 47 countries in the last 30 days.

Every request to our search, listing, and llms.txt endpoints gets classified server-side from its User-Agent. “AI assistants” only counts named systems. Generic crawlers and unclassified agents are counted separately, so the two numbers never get blended into one.

20.0%
74.0%
  • AI assistants: 17,183 (20.0%)
  • Other crawlers & bots: 63,585 (74.0%)
  • Human browsers: 5,165 (6.0%)
  • Unclassified: 1 (<0.1%)

AI assistants & their crawlers

17,183 hits · 20.0% of traffic

Chat and agent traffic from Claude, ChatGPT, Gemini, Perplexity, Cursor, Copilot, and Windsurf, plus the crawlers those companies run to index content, like ClaudeBot and GPTBot.

  • ClaudeBot (Anthropic crawler)16,937 · 19.7%
  • Gemini / Google181 · 0.2%
  • Jackalope42 · <0.1%
  • Claude / Anthropic11 · <0.1%
  • ChatGPT / OpenAI10 · <0.1%
  • Perplexity AI2 · <0.1%

Other crawlers & bots

63,585 hits · 74.0% of traffic

General-purpose web crawlers, link-preview bots, and unnamed automated clients. Not AI systems, but still worth counting.

  • Custom agents43,295 · 50.4%
  • Meta / Facebook bot16,357 · 19.0%
  • Amazonbot3,720 · 4.3%
  • Other bots & crawlers205 · 0.2%
  • Bingbot (Microsoft)7 · <0.1%
  • YandexBot1 · <0.1%

Human visitors (browser requests to the API)

5,165 hits · 6.0% of traffic

Browsers hitting API endpoints directly, separate from normal page views.

  • Browser (Human)5,165 · 6.0%

Unclassified

1 hits · <0.1% of traffic

Requests with no recognizable User-Agent pattern.

  • Unknown1 · <0.1%

What's being requested

API surfaces hit in the last 30 days, most-used first.

  • Markdown view71.3K
  • Search API12.7K
  • MCP tool calls1.4K
  • llms.txt299
  • Server detail API174
  • llms-full.txt49

Where requests come from

Top request-origin countries in the last 30 days.

  • United States82.0K
  • Germany1.2K
  • Denmark427
  • Vietnam362
  • Slovenia331
  • Paraguay224
  • South Korea132
  • Netherlands120

Why we're open about this

No login gate, no filtering. This is the same dashboard our team looks at.

Crawlers are allowlisted

Our robots.txt allows GPTBot, ClaudeBot, PerplexityBot, Google-Extended, Amazonbot, and Bytespider to read the catalog, search API, and llms-full.txt.

Built to be cited

We set ai-input=yes so answer engines and assistants can quote us directly.

Not used for training

We set ai-train=no. The catalog is available to read, not to train on.

See it yourself: robots.txt and llms-full.txt.