Neonjelly

Connect it to your AI

Claude Code

claude mcp add --transport http neonjelly https://mcp.neonjelly.io/c/%7Bconnect_token%7D/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://mcp.neonjelly.io/c/%7Bconnect_token%7D/mcp

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "neonjelly": {
      "url": "https://mcp.neonjelly.io/c/%7Bconnect_token%7D/mcp"
    }
  }
}

Tools it offers

60 tools, as the server itself reported during our check on Oct 31, 2026.

• whoamiReturn this key's plan, used today, remaining quota, rate limit, and expiry. Does not count against daily quota — call first when the user asks “what's my quota?” If remaining is 0 or trial expired, call upgrade and open
• upgradeReturn the paid upgrade URL when trial expired, daily quota is 0, or Signals is blocked. Does not count against quota. Always show the returned URL — never invent a checkout link.
• resolve_storeResolve a brand name or URL against 1.37M Shopify storefronts and return up to 5 candidates. On a single hit, also return the full store card — call this before inventing a domain; missing stores stay not_found.
• list_playbooksList composed-tool playbooks by job: store lists, VC, competitor, dropship, outreach, merch. Start here when the user has not named a tool — then call the playbook's first tool.
• get_examplesSame playbook map as list_playbooks (VC, competitor, dropship, outreach). Prefer list_playbooks on new sessions.
• brief_marketReturn a one-page TAM brief: vertical size, geos, movers, and an optional filtered cohort from 1.37M stores. Pass a vertical; quote catalog counts only — do not invent TAM.
• cohort_tamRoll a filtered store cohort into a groupBy table (country, vertical, industry, category). This is not the unfiltered get_countries TAM — use that when no filters apply.
• find_peersFind stores in the same vertical, country, and visit band as a target domain, then compare cards. Call resolve_store first if you only have a brand name.
• diligence_packBuild an IC memo for one domain: card, growth, traffic, stack roles, bestsellers, changes, and contacts. Includes Signals stats only if that domain is already watched.
• compare_stacksCompare 2–8 store app stacks: shared vs exclusive apps, tagged by role (email, support, reviews, subs, ads). Pass hostnames, not brand names.
• competitor_movesList catalog store and SKU changes plus vertical movers for one competitor domain. Ads and daily units need a paid Signals watch — do not offer create_signal on trial.
• overlap_vendorsFind product-vendor overlap and the average price gap between two stores. Use after compare_stacks when you need shared suppliers, not shared apps.
• screen_dropshipList dropship-flagged stores in a vertical/geo plus their cheapest SKUs. Country is a filter, not a login region — quote the catalog flag, do not invent supplier names.
• source_mapGroup a SKU search by vendor: store count and price min/max across the catalog. Use for sourcing or arbitrage after niche_research names the product.
• winning_skusList bestsellers, ≥10% markdowns, and new products for a vertical or one store. Require storeVertical or storeDomain — do not call empty.
• niche_researchRun semantic product-idea search plus a saturation report and the stores that sell the top hit. q is a product name or category, not a domain — quote seller count and the UNTAPPED→SATURATED verdict.
• search_product_ideasSearch product names/categories and return ideas with seller count, price, and UNTAPPED→SATURATED verdict — not one-store listings. Prefer niche_research when the user asks “is this saturated?”
• suggest_product_ideasAutocomplete product-idea names as the user types. Follow with search_product_ideas or niche_research on the chosen row.
• trending_product_ideasList product ideas the catalog marks as heating up. Pair a hit with get_product_research and list_product_sellers — do not invent trend scores.
• get_product_researchReturn the saturation report for one product idea. Copy id from search_product_ideas or niche_research — do not invent seller counts.
• list_product_sellersList stores selling a product idea, sorted by traffic or price. Copy id from search_product_ideas — this is who-sells-this, not a single merchant SKU list.
• product_searchSearch cross-store SKUs and return rows plus facets (vendors, types, stores, price band). At least one filter is required. For saturation / who-sells-this-idea, use niche_research.
• product_intelBuild one SKU memo: card, discount vs compare-at, store, SKU change history, and store bestsellers. Pass domain+handle, or q to resolve first.
• change_trackerReturn a full change board: unified feed, all 8 product change types, 5 store change types, and Signals SKU changes if watched. Prefer this over calling each change tool separately.
• price_watchList price decreases and increases across stores or one merchant. Default minPriceChangePct is 10 — raise it to cut noise.
• assortment_watchList new and removed SKUs plus bestseller enter/exit. Filter by storeDomain or productType when the user names a shop or category.
• get_contactsReturn emails, social URLs, and ESP/support app tells for one store. No phone or owner names in this catalog — pass domain or q.
• find_outreachFilter the 1.37M-store catalog, hydrate each row, and keep stores that have an email or Instagram. Caps at 10 (each costs a call) — country is a filter, not a login region.
• get_upstream_healthReturn catalog health JSON and whether auth is required. Use when a lookup fails unexpectedly — not for store research.
• search_storesFilter 1.37M Shopify stores into a list (emails/socials live on the card) or roll them up with groupBy. Without groupBy you get store cards; with groupBy you get breakdown rows, not stores. Country is a filter, not a log
• get_storeReturn one merchant card: traffic, modeled revenue, rating, apps, and socials. Call resolve_store first if you only have a brand name — missing domains stay not_found.
• compare_storesCompare 2–8 store cards side by side (traffic, revenue band, apps, rating). Missing domains land in notFound — do not invent the missing rows.
• get_store_trafficReturn monthly visits and channel mix for one store. Use after get_store when the user asks how traffic is trending.
• get_store_productsList SKUs for one merchant with price, vendor, type, and bestseller filters. Prefer this over global search_products when you already have a domain.
• get_store_appsList Shopify apps detected on one merchant. Use compare_stacks when the user wants shared vs exclusive apps across several domains.
• get_store_historyReturn daily snapshots: visits, revenue band, rating, and product counts, up to 365 days. Use for growth charts after get_store.
• get_store_changesList observation diffs for one store: revenue, visits, products, rating, apps. For a mixed product+store board, prefer change_tracker.
• search_productsSearch SKUs across the 368.9M-product catalog. At least one filter is required. For saturation or who-sells-this-idea, use niche_research.
• get_productReturn one SKU by store domain plus Shopify handle. Use get_store_products or product_search when you do not yet have the handle.
• get_product_changesList price, new, removed, position, and bestseller SKU movements. Filter by storeDomain or productType; default noise floor is minPriceChangePct.

Questions