Ask Claude, Cursor or your own scripts which ChatGPT and Google AI Mode shopping answers name your store, who they name instead, and what to fix first. For Shopify and WooCommerce merchants and the agencies that run their stores.
The command line first, then Claude reading the same data through the MCP server.
halden-outfitters
halden-outfitters $ aeosome whoamiWorkspace Halden OutfittersPlan Pro T1 (Lifetime)halden-outfitters $ aeosome dashboardPeriod (days) 30AI visibility (% of answers) 60AI visibility change (points) 0Top-3 presence (% of answers) 13.7Share of voice (%) 21.8Shopping appearance (% of answers) 29.7Answers analysed 300Products tracked 10halden-outfitters $ aeosome competitorsPeriod (days) 30Answers analysed 300Brand You Share of voice (%) Questions won Citation share (%)Ridgeline no 24.7 23 0Halden Outfitters yes 21.8 35 13.7Stridewell no 20.6 14 0Northmoor no 16.5 5 0Calder Athletic no 16.5 12 0halden-outfitters $ claude --mcp-config .mcp.json --strict-mcp-config --setting-sources project,local> Which shopping questions leave my store out, who gets named instead, and what should I fix first? Keep it short.Called aeosome: list_prompts, get_competitor_leaderboard, list_recommendations**Questions where your store isn't named** (last 30 days, ChatGPT and Google AI Mode, 0% visibility on each):| Question | Who gets named instead ||---|---|| best shoes right now | Calder Athletic || my old shoes finally gave out — what should I look at? | Calder Athletic || top rated shoes for everyday use | Calder Athletic || shoes that lasts longer than mine did | No brand named || good shoes under $89.00 | No brand named || good shoes under $98.00 | No brand named |- **Calder Athletic** is the brand that replaces you on all three broad shoe questions.- **The other three questions name no brand at all.** No one has claimed them yet, so they should be the easiest to win.- **Overall:** Ridgeline has the most share of voice at 24.7%. Your store is second at 21.8%, down 3.7 points. Google AI Mode names you about half as often as ChatGPT does (9.3% vs 18%).**What to fix first:**1. **Add an `llms.txt` file.** It's a plain-text file at your site's root that tells AI tools what you sell and where your policies are. It's the only high-priority fix on the list, it covers the whole site, and it takes minutes. The tool doesn't link it to any specific missed question, though, so treat it as a general improvement rather than a sure fix.2. **Add a FAQ section with FAQ markup to the budget product pages.** The tool links this fix to the "under $89" question (and, for a second product, to none). FAQs that answer price, durability and everyday wear directly fit the three questions no brand has claimed.3. **Skip the low-priority fixes (social-sharing preview images and product video) for now.** The tool lists the Calder questions as evidence for the preview-image fix, but a social-sharing image is unlikely to be why an AI names Calder instead of you.
Halden Outfitters, an example store we built. The commands and answers are as they ran.Recorded 11 October 2026
Built for the way stores and agencies already work
Store owners
Your Monday brief, in Claude
Ask for the week in one paragraph: what slipped, which rival was named instead, and what changed.
aeosome brief
Agencies
One report per client, scripted
Create a key in each client's workspace and pull every number as JSON into the report you already send.
aeosome competitors --json
Developers
Alerts from a scheduled job
Send new visibility drops and rivals to Slack or email. Each failure exits with its own code, so a revoked key never passes silently.
aeosome alerts --json
Content editors
Product pages, fixed from Cursor
While you edit a product page, ask which shopper questions leave it out and which sources the answers cite instead.
aeosome prompts --missing-brand true
Two ways in
Create a key in Settings, Integrations, then connect either way. Both read the same data.
MCP server
For Claude, Cursor and any assistant that speaks MCP. The assistant picks the right tool for your question on its own.
The same data as your dashboard. Each is a CLI command and an MCP tool.
whoami
The workspace and plan this API key belongs to.
brief
One-paragraph status of the store's AI visibility this week: what slipped, which rival is named instead, and what changed.
today
What moved, what to do and what was proved since a cursor (default the last 24 hours, at most 30 days). Pass the returned cursor as since on the next call to read only what is new.
dashboard
Headline AI visibility KPIs with trend against the prior period: visibility, top-3 presence, share of voice, citation health, shopping appearance.
share-of-voice
Share of brand mentions in AI answers against competitors, optionally for one engine.
products
Tracked products with their store URLs.
prompts
Shopper questions sent to AI engines, whether the store was named, and which engines showed it. Use a question id with get_prompt_responses.
responses
The full AI answers to one shopper question, per engine, with the products and sources each answer cited.
competitors
Competitors ranked by share of voice in AI answers, with prompts won and citation share.
citations
The domains AI engines cite most in answers about the store's products.
opportunities
Sites that AI engines cite for competitors but never for the store: the outreach list.
fixes
Fixes to raise AI visibility, with priority, expected impact and step-by-step implementation guides.
fix-check
Whether AEOsome can write a fix to the store, which field it changes, its current value and a suggested one.
feed
The product feed AI shopping surfaces read (OpenAI and Google formats): how many products are in it, which are left out and why, and whether the plan downloads or hosts it.
progress
Open issues by category, fixes applied in the last 7 and 30 days, and the measured visibility change after fixes.
alerts
Recent alerts: visibility drops, new competitors, and findings.
usage
Plan limits and current usage: products, answers this month, team seats and the billing period end.
apply-fix
Write a fix's value to the product in a Shopify store. Call check_fix first for the field, the current value and the suggested one. The product is re-measured after.
mark-applied
Record a fix the merchant made outside AEOsome (theme, app, another tool). The product is re-measured after.
dismiss
Dismiss a fix the merchant does not want. A dismissed fix cannot be reopened, so ask first.
Reads by default, and yours to revoke
A key reads one workspace. On a paid plan you can let a key apply fixes too, and nothing else. Revoke it in Settings and it stops working at once. API access comes with every plan, Free included.
Yes. AEOsome runs a remote MCP server at https://api.aeosome.com/mcp. Connect it to Claude, Cursor or another MCP client with an API key, then ask which ChatGPT and Google AI Mode shopping answers name your Shopify or WooCommerce store, which name a competitor instead, and what to fix first.
Yes. The aeosome command line prints tables for people and JSON for scripts with --json. Each kind of failure, such as a revoked key or a plan without API access, exits with its own code, so a cron job or CI step can act on it.
Any MCP client that accepts a server URL and an Authorization header, including Claude Code and Cursor. For a client that only runs local servers, the command line's aeosome mcp command runs the same tools over stdio.
ChatGPT and Google AI Mode. AEOsome asks them the questions your shoppers ask and records which answers name your store, which name a competitor, and which sources they cite.
Only if you allow it. A key reads one workspace by default. On a paid plan you can create a key that also applies, marks done or dismisses fixes; it cannot change settings, start a scan, invite anyone or touch billing. Revoke it in Settings and it stops working at once.
Every plan, Free included: API keys, the MCP server and the command line read your workspace on any plan.
Shopify's Storefront MCP lets an AI agent search your catalog and build a cart, and its Dev MCP helps developers build on Shopify. AEOsome's MCP server reports whether AI assistants recommend your store when shoppers ask, who they name instead, and what to change.
Yes. Create a key in each client's workspace, so every script or assistant sees only that client's data, and revoking one key leaves the others working.
Find out which AI answers name your store.
We ask AI assistants the questions your shoppers ask.
Free scan, no account.
We load analytics and affiliate tracking only if you agree. Cookie policy.