Tool · Remote signal scan
Agent-Ready Check
Can an AI agent actually use your design system? Paste your docs-site URL and we probe the five signals of the Agent-Ready Index — llms.txt, a shadcn-style component registry, W3C DTCG tokens, an MCP endpoint, and Figma Code Connect — from public URLs only, and score what we can confirm.
Try: · · ·
How it works
We probe your origin for the canonical URLs of each signal, in parallel, server-side: llms.txt and llms-full.txt; the shadcn registry paths /r, /registry.json, and /r/index.json; token files parsed and walked for W3C DTCG $value/$typekeys; and the MCP transport paths /mcp and /api/mcp. Every "yes" links the URL that proved it.
Honest caveats
A remote scan proves presence, not absence. MCP is reported as "unknown, leaning yes" at best because confirming it requires an initialize handshake we deliberately don't run; Code Connect is never remotely visible; and anything shipped via npm, GitHub, or a second domain won't appear here. A low score means "not discoverable at this origin" — the full audit determines whether that's a publishing gap or a real one.
Use it from CI or scripts
The checker is a public endpoint — wire it into CI to catch an agent-readiness regression (a dropped llms.txt, a broken registry) before your users' agents do:
curl -s -X POST https://www.designsystems.one/api/agent-ready-check \
-H "Content-Type: application/json" \
-d '{"url":"your-design-system.dev"}' | jq '{score, checks}'