Agent-friendly scorer

Can AI agents shop your store?

A free AI agent readiness checker for ecommerce. Scan any storefront URL to get a score, a breakdown per check, and a prompt you can paste into your coding agent to fix each gap.

Free, no signup. We fetch public pages over HTTP, the way an agent would.

your-store.comExample report
51
DHard for agentsout of 100 · 5 pages sampled
  • Access83
  • Product data32
  • Discovery67
  • Operability60
  • Agentic commerce0
  • FailProduct JSON-LD meets merchant listing requirements
  • Partialrobots.txt allows AI search and user agents
  • PassAI agents are not blocked or challenged

What we check

See all checks
  • Access

    Agents and AI search bots can reach your pages without blocks, CAPTCHAs or walls.

    25% of score
  • Product data

    Price, stock and variants are in the HTML and in valid Product JSON-LD.

    25% of score
  • Operability

    Add to cart, variant pickers and search are real, labelled controls.

    20% of score
  • Discovery

    Sitemaps, canonicals, fast pages and a machine-readable entry point.

    15% of score
  • Agentic commerce

    UCP profile, agent endpoints and cart permalinks for checkout by agents.

    15% of score

What is an agent-ready store?

An agent-ready ecommerce store is one AI agents can reach, read and act on: AI search bots and shopping agents are not blocked, product facts are in the HTML and in structured data, add-to-cart and search are real controls, and the store publishes machine-readable entry points like a sitemap, llms.txt or a UCP profile. This scorer runs 24 checks (plus 5 bonus signals) over plain HTTP and grades the result from A to F.

Read the agent-ready ecommerce guide

Frequently asked questions

How does the agent readiness scorer work?
It fetches your homepage, robots.txt, sitemap and up to three product pages over HTTP, the way an AI agent would, without a headless browser. Each of the 24 checks passes, partially passes or fails; checks that could not run are marked inconclusive and left out of the score. Category scores are weighted into a 0–100 score and an A–F grade.
Does blocking GPTBot or other AI training crawlers lower my score?
No. Blocking training crawlers such as GPTBot, ClaudeBot or Google-Extended is your choice and is reported for information only. Blocking user-initiated agents (like ChatGPT-User or Claude-User) and AI search bots (like OAI-SearchBot or PerplexityBot) does lower the score, because it hides your products from shoppers using AI assistants.
Which ecommerce platforms does it support?
Any public storefront URL, on any platform. When the scanner detects a Medusa store or a Next.js storefront, the fix prompts include steps specific to that stack.
Is it free?
Yes. There is no signup. Results for the same URL are cached for 10 minutes and scans are rate limited per IP address.
Can an AI agent run a scan?
Yes. Send POST /api/scan with a JSON body like {"url": "https://example-store.com"}. The response format and error codes are documented in /llms.txt.

Run your store on a platform built for agentic commerce

Medusa is open-source, headless commerce with a full Store API agents can call and storefronts you control end to end.

Deploy on Medusa Cloud

Open-source commerce with a full Store API, hosted and scaled for you. Your storefront, your data model.

Storefront skills for coding agents

Teach Claude Code, Cursor or Codex to build storefronts with the patterns these checks look for.

npx skills add medusajs/medusa-agent-skills
View the skill on GitHub