Get products ready for AI search with Windsurf
Getting products ready for AI search with Windsurf means asking the Cascade agent to read a product's GEO score in StoreSEO, fix the criteria a tool can fix, and rewrite a thin description from your own answers, all from the editor where your theme is already open.
Last updated: October 2026
Set up Windsurf for StoreSEO
Skip this if Windsurf is already connected. The full guide, with the alternatives, is on the Windsurf page.
- 1
Add StoreSEO to mcp_config.json
In the Cascade panel, open the ... menu and click the Open MCP config file icon in the MCPs section. Add the entry under mcpServers and save. Remote servers use serverUrl.
JSON{ "mcpServers": { "storeseo": { "serverUrl": "https://mcp.storeseo.com/mcp" } } } - 2
Sign in to your store
Windsurf supports OAuth for remote servers. When it asks you to sign in to storeseo, a browser window opens: pick your Shopify store and approve access. Then ask this to confirm the connection.
PromptUse StoreSEO to show me my store's SEO score breakdown.
How does this work in Windsurf?
You sit in the Cascade panel with your Shopify theme repository open, and you type something like make Merino Beanie ready for AI shopping agents, preview first. Cascade calls storeseo_start, which returns the conversation id every other tool needs along with a GEO overview of your products, then storeseo_get_resource_seo for that product. The product's geo block lists the score and each AI readiness criterion that passes or fails: FAQs, the AI snippet, image alt text, product schema and the description itself. Those first calls are reads and show up in the panel as plain tool calls.
From there Cascade works in the order the job needs. If product schema is off, it can read the setting with storeseo_get_schema_settings and ask before turning it on with storeseo_update_schema_settings, which is a store-wide switch. It then calls storeseo_preview_resource_optimization to generate FAQs and an AI snippet and to project the new SEO and GEO scores without saving anything; that spends AI credit, and StoreSEO tells the agent to say so first. Because you are in an editor, you can ask Cascade to paste the previewed FAQs next to the product template you are editing, or compare the projected checklist with a fix list kept in the repository, before you say apply.
For a thin description, Cascade runs storeseo_scan_product_description and puts StoreSEO's questions to you in the chat, word for word and in order: materials, dimensions, what is in the box and so on. You type your answers right there, and Cascade passes them to storeseo_write_product_description. Criteria only you can fix, such as the product title, price or the focus keyword, come back as a single link to the product's fix page rather than a link per criterion.
-
You: Make Merino Beanie ready for AI search. Preview first.
- storeseo_start read-only
- storeseo_get_resource_seo read-only
-
Windsurf: The beanie has a GEO score of 38. It has no FAQs and no AI snippet, and two images lack alt text. A preview spends AI credit and writes nothing. Do you want me to run it?
-
You: Yes, run the preview.
- storeseo_preview_resource_optimization preview
-
Windsurf: The preview adds four FAQs and an AI snippet and projects the GEO score to 71. Apply the FAQs and the snippet to the product?
-
You: Yes, apply both.
- storeseo_apply_resource_optimization needs approval
What to ask Windsurf
Use StoreSEO to find my five products with the lowest GEO score and list what each is missing for AI shopping agents. Read only.
Make the product Merino Beanie ready for AI search: check its GEO criteria, then preview FAQs and an AI snippet and tell me the credit cost first.
Scan the description of Ceramic Pour Over for AI agents, ask me StoreSEO's questions one by one, and keep the old description in a file called old-description.html here.
- 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 Windsurf 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 Windsurf
Windsurf's MCP documentation does not describe how Cascade approves tool calls, so you cannot count on the editor to stop the description write. StoreSEO's instruction to ask first is something the agent follows, and storeseo_write_product_description saves to Shopify at once with no undo and no revision history. Before you say yes, ask Cascade to save the previous description from the write response into a file in your repository. Also check which agent you are in: the MCP page applies to the legacy Cascade agent, while the Devin Local agent reads its own configuration files.
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 Windsurf rewrite a product description without me answering questions?
Only if you decline to answer or authorize a bulk run without them. By default Cascade scans the description, puts StoreSEO's questions to you in the chat, and passes your answers to the write step so the new copy states your facts instead of guesses.
Does the product need anything before Cascade can scan its description?
Yes. The product needs a focus keyword, which you set in the StoreSEO app, because no tool can set one. The scan and the rewrite both spend AI credit, and the product's fix page link covers anything only you can change.
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 Windsurf guides