Audit your store's SEO with Kimi Code
Running a store SEO audit in Kimi Code means typing one question into Moonshot AI's terminal agent, letting it read your StoreSEO scores and per-criterion checklists through MCP, and getting back a ranked worklist in the same session where you edit your theme.
Last updated: October 2026
Set up Kimi Code for StoreSEO
Skip this if Kimi Code is already connected. The full guide, with the alternatives, is on the Kimi Code page.
- 1
Add StoreSEO to Kimi Code
Create or edit ~/.kimi-code/mcp.json so every project on your machine can use StoreSEO. For one repository only, use .kimi-code/mcp.json inside it. You can also run /mcp-config in Kimi Code and have it add the server for you.
json config{ "mcpServers": { "storeseo": { "url": "https://mcp.storeseo.com/mcp" } } } - 2
Sign in to your store
Start a new Kimi Code session (a server added mid-session registers in the next one), run this command, then follow the browser window: pick your Shopify store and approve access.
new message to Kimi Code/mcp-config login storeseo
Step-by-step guide in the docs: How to connect StoreSEO MCP to Kimi Code
How does this work in Kimi Code?
You start kimi in the folder you normally work from, which for many Shopify developers is the theme repository, and ask something plain such as which products score lowest and what each one is missing. Kimi Code calls storeseo_start first, because every other StoreSEO tool needs the conversation id it returns, and that call also hands back a snapshot of how many products, collections, pages and articles are optimized. It then calls storeseo_list_resources with the lowest scores first and storeseo_get_resource_seo on the worst candidates. Kimi Code starts in Always Ask mode, where read-only tool calls run without a prompt, so an audit scrolls past with no approval panel at all.
The terminal changes what you can do with the result. Because the agent already has the repository open, you can ask it to write the worklist to a file, for example seo-worklist.md at the project root, or to split the findings into what StoreSEO can generate and what needs a Liquid change. Products also carry a GEO score for AI shopping agents, so a good follow-up is which listings are weakest for AI search. Criteria that no tool can fix, such as choosing a focus keyword, come back as items for you to handle in the StoreSEO app.
If the tools are missing on the first try, the cause is almost always timing. A server added to ~/.kimi-code/mcp.json while Kimi Code is open registers only in the next session, so quit, start kimi again and run /mcp-config login storeseo before you ask. Once the audit has given you a worklist, the next step is a preview in the same session, and that is where the approval behavior starts to matter.
-
You: Use StoreSEO to audit my store and save a worklist as seo-worklist.md.
- storeseo_start read-only
- storeseo_list_resources read-only
- storeseo_get_resource_seo read-only
-
Kimi Code: Illustrative result: 31 of 96 products are not optimized, and the lowest six score between 12 and 26. Four lack a meta description, and two have no focus keyword, which you set in the StoreSEO app. I wrote seo-worklist.md with the six in order. Want me to preview meta for the first one?
What to ask Kimi Code
Tap a prompt to copy it, then paste it into Kimi Code.
What StoreSEO does: store seo audit
StoreSEO scores every product, collection, page and blog post against its SEO checklist, and scores products for AI readiness (GEO) as well. An agent opens a session, lists the weakest resources first and reads the per-criterion analysis for each, so you get a ranked worklist instead of a dashboard to click through.
- 1
Open a StoreSEO session
The agent calls the start tool first. It returns a conversation id every later call needs, plus a snapshot of your store: how many resources are optimized, need improvement or are not optimized, image status, rank tracking and which features are set up.
- 2
List the weakest resources
It lists products, collections, pages or articles sorted by score, lowest first, or filtered to the ones marked not optimized. Products also carry a GEO score and their AI-readiness issues.
- 3
Read the checklist for each one
For each candidate it reads the full SEO record: current meta fields, focus keyword, score, every criterion that passes or fails, image status, FAQs and AI snippet.
- 4
Sort fixes by who can make them
It separates what a StoreSEO tool can fix (meta, handle, FAQs, AI snippet, image alt text, schema) from what only you can change in the app or in Shopify admin (the focus keyword, the product title, category, inventory).
- 5
Report a worklist
You get the resources in order, with the failing criteria in plain words and one suggested next fix. Nothing is written during an audit.
Store SEO audit reference
| Resource types | Products, collections, pages and blog articles |
|---|---|
| Scores | An SEO score for every resource, plus a GEO (AI readiness) score for products |
| Status labels | Optimized, needs improvement, not optimized; GEO adds not analysed |
| Sorting | By score, lowest first, or filtered to not optimized |
| Session | Every call carries the conversation id from the start tool; calls without it fail |
| What it writes | Nothing. Every audit tool is read-only |
| Fixed only in the app | Focus keyword choice, product title wording, Shopify category, product type, inventory, variant data |
| Plan | Any active StoreSEO plan, including the free plan |
Rules Kimi Code follows
- Every audit call is a read and runs straight away; nothing in this job changes your store.
- The agent describes criteria by their visible title, never by internal identifiers or raw status values.
- Criteria no tool can fix, such as choosing the focus keyword, are handed to you with a link into the StoreSEO app rather than guessed.
- The agent should offer one next fix at a time, tied to what it just found, instead of dumping the whole list as a checklist.
In Kimi Code
Kimi Code runs read-only calls straight away in its default mode, which suits an audit, but remember the setting when the audit turns into fixes. If you switched to /yolo or /auto earlier in the day, StoreSEO's preview and apply tools stop prompting too, and the only check left is the confirmation StoreSEO tells the agent to ask for. Switch back to the default mode before you move from reading scores to changing them, or keep a permission rule that leaves the write tools on ask.
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
Does a StoreSEO audit in Kimi Code ask me to approve each call?
Not in Always Ask mode. The audit tools storeseo_start, storeseo_list_resources and storeseo_get_resource_seo only read, and Kimi Code runs read-only calls without a prompt. Prompts appear later, when a tool writes or spends credit.
Can Kimi Code save the audit into my theme repository?
Yes, it can write a Markdown or CSV file into the folder it was started in, since it edits project files. The StoreSEO calls themselves change nothing in your store, but file writes follow Kimi Code's own approval setting.
Does an SEO audit change anything in my store?
No. The audit uses read-only tools: the session start, the resource list and the per-resource SEO record. Your store is only changed later, by a separate step you agree to.
What is the difference between the SEO score and the GEO score?
The SEO score measures a resource against StoreSEO's on-page checklist for search engines. The GEO score applies to products only and measures how ready the product is for AI shopping agents and generative search, using criteria such as FAQs, an AI snippet, alt text and product schema.
Can the agent choose my focus keyword?
No tool can set the focus keyword. The agent can tell you when the keyword is missing or looks wrong and give you a link to set it in the StoreSEO app, and several fixes such as keyword clusters and description writing need it set first.
How many products can the agent audit at once?
The listing is paginated, so the agent can walk your whole catalog page by page. In practice it is more useful to ask for the lowest scores first and work down from there.
Keep going
Store SEO audit with other agents
More Kimi Code guides