AI search readiness Get products ready for AI search with Claude Code
Getting products ready for AI search with Claude Code means asking Anthropic's terminal agent to read a product's GEO score in StoreSEO, check whether product JSON-LD is on, and apply the FAQs and AI snippet you approve without leaving your repository.
Last updated: October 2026
Set up Claude Code for StoreSEO
Skip this if Claude Code is already connected. The full guide, with the alternatives, is on the Claude Code page.
- 1
Add StoreSEO to Claude Code
Run this in any terminal. The user scope makes StoreSEO available in every project on your machine.
Terminalclaude mcp add --transport http --scope user storeseo https://mcp.storeseo.com/mcp
- 2
Sign in to your store
Start Claude Code, run /mcp, choose storeseo and follow the browser window: pick your Shopify store and approve access.
Prompt/mcp
How does this work in Claude Code?
You run Claude Code from the folder you already work in, often the theme repository, and type a request in plain words: check why the Merino Beanie scores low for AI search and fix what you can. It calls storeseo_start, then storeseo_get_resource_seo, and each call scrolls past in the terminal with its name. The geo block in the result lists the AI-readiness criteria. A typical gap is that product schema is off, which is a shop-wide setting rather than a product setting, so Claude Code should tell you that turning it on credits the schema criterion on every product before it calls storeseo_update_schema_settings.
Developers get one thing here that chat users do not: the agent can see your code. If the theme already prints its own Product JSON-LD in a snippet, ask Claude Code to compare that markup with what StoreSEO would publish before you enable the schema, so you do not ship two competing Product blocks. That check is about files in your folder, and StoreSEO plays no part in it. After the schema decision, Claude Code calls storeseo_preview_resource_optimization, which generates FAQs and an AI snippet and projects the new SEO and GEO scores without saving. It spends AI credit, and the draft expires after an hour.
You approve in the conversation, and Claude Code then calls storeseo_apply_resource_optimization. The apply returns the re-analysed checklist, so Claude Code can report which criteria now pass and which still need you, with one link to the product's fix page rather than one per item. If you stop before applying and the agent turned schema on only for this flow, it should switch that schema back off. Longer runs can be written to a Markdown file in the repository so the worklist survives the session.
-
You: Why does the Merino Beanie score low for AI search? Fix what you can.
- storeseo_start read-only
- storeseo_get_resource_seo read-only
-
Claude Code: GEO is 41. Product schema is off, and there are no FAQs or AI snippet. Schema is a shop-wide setting, so enabling it credits that criterion on every product. Turn it on?
-
You: Yes, turn it on.
- storeseo_update_schema_settings needs approval
- storeseo_preview_resource_optimization preview
-
Claude Code: Preview projects GEO 41 to 70 with five FAQs and a snippet. Want me to save the result to ai-readiness.md before you decide?
What to ask Claude Code
Use StoreSEO to read the GEO checklist for the Merino Beanie and list what is missing. Do not change anything.
Check whether product schema is enabled in StoreSEO, compare it with the JSON-LD in snippets/ in this theme, and tell me if they would clash.
Preview FAQs and an AI snippet for my three lowest GEO products, show the projected scores, and wait for my yes before applying.
- Which of my products have the lowest GEO score, and what is missing for AI shopping agents?
- Make the product Merino Beanie ready for AI search: FAQs, AI snippet and product schema. Preview first.
- Scan the description of my best seller for AI agents and ask me the questions it needs.
- Rewrite the description of Ceramic Pour Over from my answers. Keep a copy of the old one for me.
- Is product JSON-LD schema enabled on my store? If not, explain what turning it on changes.
What StoreSEO does: ai search readiness
GEO is StoreSEO's AI readiness score for products. The agent reads which GEO criteria fail, fixes the ones a tool can fix (FAQs, AI snippet, alt text, product schema), and can rewrite a thin description from your own answers to StoreSEO's questions.
Requires: FAQs, AI snippets and descriptions spend AI Content Optimizer credit. The product needs a focus keyword, set in the StoreSEO app, before a description scan or rewrite.
- 1
Read the GEO checklist
The agent reads the product's GEO block: the score and every AI-readiness criterion that passes or fails.
- 2
Turn on product schema if it is off
Product JSON-LD is a shop-wide setting, so enabling it clears that criterion for every product at once. If you then decide not to apply the rest, the agent switches back off only the schema it turned on.
- 3
Preview FAQs and the AI snippet
The preview generates FAQs and an AI snippet (summary, benefits, best for) and projects the new SEO and GEO scores without saving.
- 4
Scan the description
For a thin or missing description, StoreSEO scores it on seven pillars (identity, materials, dimensions, features, use cases, what is included, care) and returns questions. The agent asks you each one, word for word.
- 5
Write and apply
With your answers, StoreSEO writes the description and saves it immediately; the response holds the only copy of the old text. The previewed FAQs and snippet are applied after your yes.
AI search readiness reference
| Scope | Products only; collections, pages and articles have no GEO score |
|---|---|
| Fixable by tools | FAQs, AI snippet, image alt text, product schema, description |
| Fixed only in the app or admin | Product title, category, product type, image count, inventory, variant barcode, SKU, price, image |
| Description pillars | Identity, materials, dimensions, features, use cases, what is included, care |
| Description write | Saved immediately to Shopify and StoreSEO; no undo and no revision history |
| Old description | Returned once in the write response, the only remaining copy |
| Product schema | Shop-wide toggle; credits the schema criterion on every product |
| Prerequisite | A focus keyword on the product, set in the StoreSEO app |
Rules Claude Code follows
- The scan's questions go to you word for word and in order; the agent does not answer them for you.
- A description is only written without questions when you decline to answer or authorize a bulk run without them.
- Writing a description replaces the current one at once with no undo, so the agent asks first and keeps the old text the response returns.
- If the agent enabled product schema for this flow and you stop before applying, it turns that schema back off; it never disables a schema you already had on.
- Criteria only you can fix get one link to the product's fix page, not a link per criterion.
In Claude Code
Claude Code asks before a tool runs unless you added an allow rule. If you allow the StoreSEO tools to stop the prompts, that rule also covers storeseo_update_schema_settings, the apply tool and the description write, and the confirmation StoreSEO asks for in the chat becomes the only check, so keep those on ask. Without --scope user the server exists only in the project where you added it. Claude Code also warns when one tool result passes 10,000 tokens, so ask for a few products at a time, not the whole catalog.
What runs without asking. Reads such as SEO scores, store listings, settings and Google reports run straight away. Generating a preview spends AI credit but writes nothing, and StoreSEO tells the agent to say what a generation will cost before it runs one. Applying content, optimizing images, changing settings, publishing llms.txt or agents.md, writing a product description and deleting anything wait for your yes in the conversation. That yes is an instruction the agent follows, not a lock on the server, so your client's own tool-approval setting is the hard stop.
Questions
Can Claude Code compare my theme's JSON-LD with StoreSEO's product schema?
Claude Code can read the Liquid and JSON-LD files in your folder, and StoreSEO tells it whether product schema is enabled through its settings tools. Comparing the two is the agent's own work, so it is worth asking for before you switch the shop-wide schema on.
What happens if I stop after Claude Code enabled product schema?
StoreSEO's workflow tells the agent to switch off only the schema it turned on for this flow if you decide not to apply the rest, and to leave a schema you already had on. Check the result with the schema settings tool if you are unsure.
What is a GEO score in StoreSEO?
GEO is StoreSEO's AI readiness score for products. It measures how well a product can be understood by AI shopping agents and generative search, using criteria such as FAQs, an AI snippet, image alt text, product schema and the quality of the description.
Can I undo a rewritten product description?
Not inside StoreSEO. The new description is saved immediately and StoreSEO keeps no revision history. The response returns the previous description once, so ask the agent to keep it for you before it writes.
Why does the agent ask me questions before writing a description?
StoreSEO scans the description on seven pillars and returns questions for the facts it cannot infer, such as materials or what is in the box. Your answers become stated facts in the new copy instead of guesses.
Does enabling product schema affect every product?
Yes. Product JSON-LD is a shop-wide setting, so turning it on clears that criterion for every product at once, and turning it off removes it everywhere.
Keep going
AI search readiness with other agents
More Claude Code guides