Store SEO audit

Audit your store's SEO with Codex

Auditing your Shopify store's SEO with Codex means asking OpenAI's terminal agent, signed in to the StoreSEO MCP server, which products, collections, pages and posts score worst, and having it read each checklist and report a worklist in the terminal or in a file.

Jump to the prompts Connect Codex

Last updated: October 2026

Set up Codex for StoreSEO

Skip this if Codex is already connected. The full guide, with the alternatives, is on the Codex page.

1
Add StoreSEO to Codex

Run this in any terminal. It writes a [mcp_servers.storeseo] table to ~/.codex/config.toml, which the Codex CLI, the IDE extension and the ChatGPT desktop app all read.
Terminal

codex mcp add storeseo --url https://mcp.storeseo.com/mcp
2
Sign in to your store

Run the login command. Your browser opens: pick your Shopify store and approve access. Then run codex mcp list, or type /mcp inside Codex, to confirm storeseo is there.
Terminal

codex mcp login storeseo codex mcp list

How does this work in Codex?

You run codex in your project folder, after signing in with codex mcp login storeseo, and type the request in plain words: which products score worst and what is wrong with each. Codex lists its tool calls as it goes. It calls storeseo_start first to open the session, then storeseo_list_resources sorted by score, lowest first, then storeseo_get_resource_seo for each product it needs to describe. All three are read tools, so the run is a listing and reading exercise with no change to the store.

The terminal makes the audit easy to repeat and to reuse. Ask Codex to write the worklist to a file in the folder, such as seo-audit.md, and it will, which gives you something to diff against the next run. You can also ask for it in a form that suits your workflow, a list of product handles to batch through later or a table grouped by shared problem. Codex keeps the separation StoreSEO asks for: it reports which fixes a StoreSEO tool can make, such as meta, FAQs and image alt text, and which only you can make, such as the focus keyword and the product title.

Codex reads a config file for the server, so how you set approval in config.toml is worth a look before the first run. For audits, the read tools can run without prompts, but keep the server's approval mode on writes or prompt so a later apply or generate still stops for a decision. Codex also waits 60 seconds for a tool by default, which is plenty for reads.

Codex + StoreSEO Illustrative session

You: Audit my Shopify SEO and list the products with the lowest scores.
storeseo_start read-only
storeseo_list_resources read-only
storeseo_get_resource_seo read-only
Codex: The lowest twenty products score between 11 and 36. Missing meta descriptions and image alt text are the most common gaps, and three products have no focus keyword, which you set in the StoreSEO app.
You: Write that to seo-audit.md.
Codex: Written. Want me to preview the meta for the products missing a meta description?

What to ask Codex

Prompt 1

Use StoreSEO to list my twenty lowest-scoring products and the main failing criterion on each. Read only.

Prompt 2

Audit my collections and pages, worst first, and write the worklist to seo-audit.md, split into fixes StoreSEO can make and fixes I must make.

Prompt 3

Which products have the weakest GEO score? Give me their handles and the issue on each.

Show me my ten lowest-scoring products and the top issue on each.
Which collections are not optimized yet, and what is failing on them?
Give me an SEO audit of my blog posts, worst first.
Which products have the weakest GEO score for AI shopping agents, and why?
Summarize my store's SEO: how many products, collections, pages and posts are optimized?
For the product Linen Shirt, list every failing SEO criterion and say which ones StoreSEO can fix.

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.

storeseo_startstoreseo_list_resourcesstoreseo_get_resource_seo

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 Codex 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 Codex

Set the storeseo server's default_tools_approval_mode to writes or prompt in config.toml, not approve. An audit does not need approve, since every audit tool is a read, and approve would also silence the prompts for the apply and generate tools you may use next, leaving only the confirmation StoreSEO asks for in chat. A project-level .codex/config.toml loads only in trusted projects, so if Codex does not see StoreSEO in a project, use ~/.codex/config.toml instead.

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

How do I sign Codex in before running a StoreSEO audit?

Run codex mcp login storeseo, pick your Shopify store in the browser and approve access. If you prefer a token, create one in StoreSEO under Settings, AI Toolkit and let config.toml read it from an environment variable.

Can Codex write the audit to a file in my project?

Yes. Ask it to save the worklist as a Markdown or CSV file in the folder you ran codex from. The audit itself only reads from StoreSEO, so the only file written is the one you asked for.

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.