AI & Agents

Agentcard

Last updated 2026-06-24 · benchmark measured 2026-08-09 — deterministic & reproducible

Agentcard issues virtual debit cards so AI agents can make purchases on your behalf.

Is Agentcard production-ready?

Legit.Show scores Agentcard 80 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Agentcard (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Privacy; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 62/100
• Accessibility — 98/100
• Security — 45/100
• Privacy — 100/100
• Reliability — 100/100
• Standards — 85/100
• Discoverability — 70/100

What we measured

• Security headers present: HSTS.
• No Content-Security-Policy.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 662 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• Has a reachable privacy policy.
• Sets cookies / loads scripts with no consent prompt.

Who built it

Karen S. (@keyserfaty)

Who it's for

AI agents · ChatGPT users · Claude Desktop users · Developers building autonomous workflows · Businesses enabling agent commerce

Visit Agentcard → · Alternatives to Agentcard → · How this was measured →