AgenticCart
AI readiness checks for online stores: check any Shopify, WooCommerce or other shop, a product page, a product feed or an llms.txt and get a score with the open issues. Read-only, no sign-in.
Hosted MCP Server
npx add-mcp 'https://agenticcart.ai/mcp'Installs into Claude Code, Codex, Cursor and more
Documentation
Free, no account Tested in Claude and ChatGPT
Audit your store inside
AgenticCart connected
Is examplestore.com ready for AI shopping assistants?
AgenticCart · check_store_readiness
40 of 100
- AI crawlers are blocked robots.txt turns away GPTBot and ClaudeBot
- No product data in the pages the sampled product page has no Product markup
- Sitemap and HTTPS both fine
Two things keep assistants out. Want me to write the Product markup for your product template?
Example. Store and figures are made up. Play again
Your store looks fine.An assistant may see nothing.
ChatGPT, Claude and Perplexity read the page your server sends, not what a browser shows. A blocked crawler, product data that only exists after JavaScript ran, a feed without identifiers: none of it is visible to you, all of it decides whether your products get recommended.
88 % of product pages carry product data an assistant can read. The other 12 % leave it guessing.
33 % state a GTIN or MPN, the number that tells an assistant two offers are the same product.
63 % of shops have an llms.txt, the file that tells assistants where to look.
From our study of 9,821 online shops, November 2026. Read the study
Five tools.One endpoint.
Each takes one address and returns a score from 0 to 100 with specific findings, not a pass or fail.
check_store_readiness
The whole store
From the homepage address: are AI crawlers allowed in, is product data in the pages, sitemap, llms.txt, HTTPS.
Takes url, e.g. https://examplestore.com
check_product
One product page
What an assistant can read on it: product data, price and availability, images, description, GTIN and brand. Says so when the page only gets its content from JavaScript.
Takes url, e.g. https://examplestore.com/products/trail-shoe
check_acp_feed
A feed for ChatGPT
Your product feed against the Agentic Commerce Protocol and OpenAI’s product feed specification, field by field.
Takes url, e.g. https://examplestore.com/feed.xml
check_merchant_feed
A Google Merchant feed
Required attributes, price format, availability values and GTIN check digits, as Google’s specification asks for them.
Takes url, e.g. https://examplestore.com/google-feed.xml
check_llms_txt
The llms.txt
Read and checked against the llmstxt.org format: title, summary, link sections, dead links, and whether the server really sends the file.
Takes url, e.g. https://examplestore.com
The diagnosis is free.The fixes come with a plan.
Every issue is named without an account, so you always see the whole picture. What to change for each one comes with any AgenticCart plan, through the licence key already in your dashboard.
Without an account
Free
No sign-up, no card. 10 checks per hour.
- All five tools
- Score and grade
- Every issue named, grouped by severity
- What to change, for one issue as a sample
- What to change, for every issue
- The full result as data for your agent
With any plan
From $29.99 a month
Included in every plan. 300 checks per hour.
- All five tools
- Score and grade
- Every issue named, grouped by severity
- What to change, for one issue as a sample
- What to change, for every issue
- The full result as data for your agent
Already a customer? Send the licence key from Dashboard > API Key as a Bearer token and every check comes back complete.
Prompts that work.
Copy one, put in a real address, paste it into your assistant.
Audit a store
Use AgenticCart to check whether examplestore.com is ready for AI shopping assistants, then summarise the three most important fixes.
Fix a product page
Check examplestore.com/products/trail-shoe with AgenticCart and write the JSON-LD I need to add to fix what it found.
Check while building
I just changed the product page. Run the AgenticCart product check again and tell me what changed in the score.
Debug a feed
Grade my product feed at examplestore.com/feed.xml against the Agentic Commerce Protocol and tell me which fields are missing.
Compare stores
Run the AgenticCart store readiness check on these three stores and put the scores in a table with the biggest gap for each.
Check the llms.txt
Check the llms.txt of examplestore.com with AgenticCart and tell me what to fix first.
Questions,answered.
Something else? We usually reply within a few hours.
Do I need an AgenticCart account?
Not to try it. Without any credentials you get the score and every issue named and grouped by severity, plus what to change for one of them as a sample. What to change for the other issues comes with any AgenticCart plan. All five tools work on both; the difference is the detail, never the diagnosis.
Which AI assistants can use it?
Any client that connects to a remote MCP server over HTTP. We tested it in Claude, in ChatGPT and in Claude Code in November 2026; the steps for each are on this page. It is a remote endpoint, so there is nothing to install and nothing running on your machine.
What can it check?
Five things: a whole store from its homepage, a single product page, a product feed against the Agentic Commerce Protocol, a product feed against the Google Merchant Center specification, and a site's llms.txt. Each returns a score from 0 to 100 with specific findings rather than a pass or fail.
Does it work on stores I do not own?
Yes. Everything it reads is public: the pages, the robots.txt, the sitemap and the feed. An agency can audit a client's or a competitor's store before it has any access.
Can it change anything in my store?
No. The server only reads. It fetches public addresses and analyses them. It cannot write to a store, cannot read anything behind a login, and has no access to any AgenticCart account, catalog or conversation. Requests aimed at private or internal network addresses are refused.
What are the limits?
Ten checks per hour without a key, counted per IP address. With a plan it is 300 per hour, counted per account, so a team behind one shared connection does not share one budget. Reaching the limit is not an error in your request: your assistant is told to wait and can try again. Both limits are separate from the ones on the tools on our website.
Why is my score low even though my store looks fine?
A store that looks fine to a person can be unreadable to an assistant. The usual causes: AI crawlers blocked in robots.txt, no product data in the HTML, pages that only get their content from JavaScript, no llms.txt, and feeds without GTIN or MPN. None of these show in a browser.
How do I get the full findings?
Take the licence key from Dashboard > API Key in your AgenticCart account and send it to the MCP server as a Bearer token. Every plan includes it; there is no separate MCP subscription. If the key is missing or wrong, or the subscription is no longer active, the server returns the free result and says why instead of failing.
Is it the same as the checkers on your website?
The same checks and the same scores. The difference is where the result lands. A web form gives you a report you then act on by hand; a tool result lands in the conversation with everything else your assistant can do, so it can read the findings, explain them and write the fix.
Can I use it in my own agent?
Yes. It is a standard MCP server over HTTP: JSON-RPC 2.0 by POST, with the methods initialize, ping, tools/list and tools/call. Any client or framework that speaks MCP can connect to the same endpoint.
Check your store beforeyour customers’ assistants do.
Add it to your assistant and ask. When you want the fixes prepared across your whole catalog, start the 7-day free trial.
Free to check · No account · Read-only
No assistant at hand? The same checks run on our website as free tools.