Make your AI a shadcn expert

get_registry_stats

Top-level counts across every shadcn.io surface — blocks, components, hooks, charts, icons. One call, bird's-eye view. Cached for 10 minutes.

get_registry_stats is the "what's on shadcn.io?" bird's-eye view. One call returns the counts for every surface plus icon totals — no need to enumerate each surface separately.

When to use it

  • Onboarding / marketing questions ("what can I build with shadcn.io?").
  • Giving the user a coverage sense before a plan ("we have 56 block categories — let's pick the ones relevant to your SaaS").
  • Dashboards or internal tooling that surfaces registry health.

Arguments

None.

Example prompts

use shadcnio to give me a summary of everything available
use shadcnio get_registry_stats and tell me how many pricing-category blocks I can pick from
use shadcnio — how many icons total do I have access to?

Response shape

{
"totalItems": 6524,
"surfaces": {
  "blocks":     { "total": 6120, "categories": 56 },
  "ai":         { "total": 48 },
  "components": { "total": 82 },
  "examples":   { "total": 164 },
  "hooks":      { "total": 27 },
  "charts":     { "total": 18 },
  "button":     { "total": 12 },
  "background": { "total": 14 },
  "shaders":    { "total": 9 },
  "text":       { "total": 16 },
  "themes":     { "total": 14 }
},
"icons": {
  "libraries": 222,
  "total": 285043
},
"computedAt": "2026-04-16T14:32:18.412Z",
"cacheTtlSeconds": 600
}
  • computedAt tells you how stale the snapshot is.
  • cacheTtlSeconds declares the cache window — a well-behaved agent can trust the numbers for that window without re-asking.

Manual invocation

curl -s -X POST "https://www.shadcn.io/api/mcp?token=YOUR_TOKEN" \
-H "content-type: application/json" \
-H "accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_registry_stats","arguments":{}}}' \
| sed -n 's/^data: //p' | jq '.result.content[0].text | fromjson'

FAQ

Was this page helpful?

Sign in to leave feedback.