# Is Agentic Storefront: Check How Agent-Friendly your Ecommerce Storefront is > Source: > Published: 2026-10-15 00:00:00+00:00 [Blog](https://medusajs.com/blog) October 15, 2026·Company # Is Agentic Storefront: Check How Agent-Friendly your Ecommerce Storefront is Shahed Nasser Shahed Nasser Announcing a free tool to check your storefront's agentic score, with prompts to fix it. You can also use it with your AI agent to get your score and apply fixes. Today, we're announcing [Is Agentic Storefront](https://is-agentic-storefront.com), a free tool that checks how well your ecommerce storefront works with AI agents. Enter your store's URL and get an overall score, a score per category, and a ready-to-paste fix prompt for every check that fails. ## Why your storefront needs to be agentic Shoppers increasingly ask AI assistants like ChatGPT, Claude, and Perplexity to find, compare, and buy products for them. These agents don't browse like people. They read raw HTML, parse structured data, and call APIs. If an agent can't reach your store, read your prices, or find the add-to-cart button, it moves on to a store it can use. Being agentic means your store is visible and buyable in that channel, not only in a browser. ## How we score your storefront The scanner fetches your homepage and a sample of product pages over plain HTTP, the same way most agents do. It runs 29 checks grouped into five weighted categories: - **Access:** agents and AI search bots aren't blocked by robots.txt, bot challenges, or CAPTCHAs. Blocking training crawlers is your choice and isn't penalized. - **Product data:** name, price, and availability are in the server-rendered HTML and in valid Product structured data. - **Discovery:** agents can find your products through sitemaps, canonical URLs, and agent-facing files like llms.txt. - **Operability:** buttons, variant selectors, and search are real, labelled controls an agent can use. - **Agentic commerce:** your store exposes a commerce protocol that lets agents build carts and check out. Every check is based on a published spec or official documentation, including: Each check has its own page on the site explaining why it matters, how the scanner tests it, and how to fix it. ## Fix prompts for every failing check A score alone doesn't tell you what to change. Every failing or partial check comes with a fix prompt: a ready-to-paste set of instructions for your coding agent, based on what the scanner found on your store. Each prompt lists the exact findings, such as a missing Copy to clipboard`price` in your Product JSON-LD or a blocked AI search bot in robots.txt. It also links to the spec the fix has to follow. Copy the prompt into Claude Code, Cursor, Codex, or any agent you're using. and let it apply the fix in your storefront's codebase. ## How Medusa stores become agentic With Medusa, you own the storefront code and the commerce backend, so every fix the scanner suggests is a change you can make yourself. There's no theme or platform setting standing between you and the fix. - **Agents can call your store directly.** Medusa's[Store API](https://docs.medusajs.com/api/store) exposes products, carts, and checkout, so agents aren't limited to scraping pages. - **Fix prompts know your stack.** The scanner detects Medusa storefronts and adds Medusa-specific notes to each fix prompt. - **Agentic checkout is documented.** Our[agentic commerce tutorial](https://docs.medusajs.com/resources/how-to-tutorials/tutorials/agentic-commerce) shows how to sell through ChatGPT Instant Checkout with a product feed and checkout APIs. ## How to use it The tool is free and needs no sign-up: 1. Go to [is-agentic-storefront.com](https://is-agentic-storefront.com) . 2. Enter your store's URL and start the scan. 3. Review your score and copy the fix prompt for any failing check into your coding agent. ## Use it from an AI agent The tool is built to be used by agents too. Give your agent a prompt like this: ``` 12Use https://is-agentic-storefront.com to check whether https://acme-store.com is agent-friendly. ``` The agent calls the scan API and summarizes the score and what to fix. You can then ask it to apply the necessary fixes directly in your codebase. ## Improve your storefront with the storefront skill Fixing your score is easier with our [storefront best-practices skill](https://github.com/medusajs/medusa-agent-skills/tree/main/plugins/ecommerce-storefront/skills/storefront-best-practices). It teaches coding agents like Claude Code, Cursor, and Codex the storefront patterns these checks look for, so your agent fixes issues the right way and builds new pages agent-ready from the start. ``` 12npx skills add medusajs/medusa-agent-skills ``` Then ask your agent to use it alongside your scan results: ``` 12Use the storefront-best-practices skill to fix the failing checks in my Is Agentic Storefront report, starting with Product structured data on product pages. ``` The skill works with any framework and backend, not only Medusa. ## Get Started with Medusa If you're new to Medusa, check out the [documentation](https://docs.medusajs.com), where you'll get a more in-depth understanding of what Medusa is, the commerce features it provides, and how to deploy Medusa to [Cloud](https://linear.app/medusajs/document/blog-is-your-storefront-agentic-check-it-for-free-398414b1c27b).