2026-09-04
Ecommerce data MCP — query 1.37M Shopify stores from chat
1.37M
Shopify stores in the catalog
368.9M
SKUs tracked
60
MCP tools (playbooks + catalog)
Source: EcomScout catalog, pulled 2026-09-04. Coverage from get_analytics_overview / GET /v1/analytics/overview.
The 40-second demo
Start a trial, look up Gymshark, see the same JSON an agent gets. Forty seconds. Screens below walk the same steps with the numbers written out.
What people actually look up
Almost nobody searches “ecommerce MCP.” They search Shopify competitors, a store list, or product research. “Shopify MCP” is Shopify’s own connector — hook your shop to an agent — not this catalog. We write for the jobs: find stores, research a product, see who competes. Search volumes sit under the tables.
| Query | Vol / mo | KD | CPC |
|---|---|---|---|
| shopify mcp | 700 | 26 | $3.00 |
| ecommerce intelligence | 200 | 1 | $5.00 |
| ai ecommerce tools | 200 | 16 | $6.00 |
| shopify product research | 60 | 7 | $2.50 |
| ecommerce data api | 50 | 3 | — |
| ecommerce mcp | 10 | 0 | — |
Source: Ahrefs Keywords Explorer. Country=us, 12-month average monthly volume. CPC is USD (API cents ÷ 100). KD 0–100. Pulled 2026-09-04.
| Query | Vol / mo | KD | CPC |
|---|---|---|---|
| mcp server | 41,000 | 31 | $3.00 |
| model context protocol | 15,000 | 85 | $2.50 |
| shopify competitors | 1,300 | 7 | $3.00 |
| shopify store database | 100 | 23 | $2.50 |
| shopify store list | 60 | 5 | $0.90 |
Source: Ahrefs Keywords Explorer. “mcp server” (41k) and “model context protocol” (15k) are the protocol, not a product. We do not chase those SERPs.
Example numbers from the catalog
Same snapshot as the US market page. The US is 605,829 stores (5.9% dropship). India is sixth — 56,821 stores, 0.9% dropship. Apparel has the most shops. Footwear has fewer shops and more visits each.
Source: EcomScout catalog, pulled 2026-09-04. GET /v1/analytics/countries. Dropship % = round(1000 × dropshippers / stores) / 10.
Source: EcomScout catalog, pulled 2026-09-04. GET /v1/stores?groupBy=vertical&minVisits=1000. Floor drops parked shops.
How to use it
- Open Start. One click starts a 14-day trial (100 lookups/day, no account) and looks up Gymshark so you see a real store card first.
- Click Connect Cursor (or Claude). Accept the prompt. You do not paste a key.
- Ask for a job — “20 US skincare emails,” “look up gymshark.com,” “is a neck fan crowded.” If a store is not in the catalog, the answer is not found. That is the end of it, not a prompt to invent a number.
Same catalog over HTTP if you want curl. The playground runs cached examples so you can read JSON without using trial quota.
Asks that hit a tool
“Look up gymshark.com — visits, modeled revenue, SKU count.”
resolve_store / get_store
“20 United States skincare stores, >10k visits, email on file.”
find_outreach
“Is a neck fan saturated? Seller count and who sells it.”
niche_research
“Vendors supplying hoodies under $25, and which stores use them.”
source_map
Demo screens, one by one
Same steps as the video. Each screen is something you can still do on the live site.
No signup form. The lime button starts a 14-day trial and looks up Gymshark so you see a real store card. Cursor is the default. Claude, VS Code, ChatGPT, and Windsurf are under the fold. 100 lookups a day. You do not paste a secret.
After the click you get a merchant card, not a spinner essay. This snapshot: gymshark.com, US, Apparel, Shopify, grade S. 15.1M modeled monthly visits, revenue band $9.4M–$20.4M, 9.5k SKUs, about $67k ad spend, rating 74. The JSON block under the bars is the same payload an agent sees. If those numbers ever disagree with chat, trust the tool — the model did not invent a second Gymshark.
Playground is for when you want to see the request. Search stores for gruntstyle — brand to domain is usually the first lookup. On-page Run is cached, so you can read the JSON without using trial quota. Use your own key in a terminal when you want a fresh row.
Grunt Style comes back: Shopify, fashion / T-shirts, US, about 1.14M monthly visits, modeled monthly revenue $370k–$802k. Different planet from Gymshark’s 15M — same lookup, different store. Once you see two cards, stop asking the model to “estimate traffic.” Ask it to compare the two stores.
Trial is store lists, product research, and what changed on a store. Competitor ads and daily units start at Explorer. Caps on this shot: Trial 100/day; Explorer $29 · 2,000/day · 8 watches; Operator $79 · 15,000/day · 20 watches; Scale $199 · 50,000/day · 40 watches. Yearly is two months free. Promo LAUNCH is 50% off the first three months, expires 31 Oct 2026.
Same catalog, four jobs: look up a store, read a price move, watch ads and units on a paid plan, ask if a product is crowded. Indexed by EcomScout. Connect starts the same 14-day trial. One sentence: the agent does not “know” 1.37M stores. It has a tool that can look one up.
Sources
- Catalog counts pulled 2026-09-04 from EcomScout — 1,367,109 stores, 700,735 with traffic, 368.9M SKUs. Reproduce with
get_analytics_overvieworget_countries. - Gymshark / Grunt Style cards:
GET /v1/stores?q=…on /start and /playground. Modeled revenue is a band, not GMV. - Keyword tables: Ahrefs Keywords Explorer, Google US, 12-month average volume, 2026-09-04. CPC from API cents ÷ 100.
- Demo video: Neonjelly.io e-commerce MCP demo. Screens from the same walkthrough used on Product Hunt / Arcade.
Run the Gymshark lookup
Also VS Code, ChatGPT, Windsurf…
Looks up the store you typed, then opens your agent. 14 days · 100/day · no card.