neonjelly

Start

Getting started

Connect Cursor, start a 14-day trial, then ask for a store, a list, or a product.

Neonjelly is Shopify research for your AI. Ask in Cursor or Claude; the agent looks up a live catalog of 1.37M stores and cites the row. You get products, traffic, prices, and lists. Competitor ads and daily units are on paid plans.

What exists today:

  • Homepage Connect or /start — mints a trial, looks up a store you pick, opens the agent. This tab stays open.
  • MCP: https://mcp.neonjelly.io/mcp (needs a key or connect URL)
  • Connect URL: https://mcp.neonjelly.io/c/<njc_…>/mcp (auth in the path)
  • 60 tools — jobs first (competitors, dropship, outreach, merch), then catalog lookups. List: /docs/tools
  • Catalog REST: https://mcp.neonjelly.io/v1 — GET-only. Same nj_ / njc_ token. See /docs/api
  • Playground: /playground — try a lookup
  • After install, ask “what’s my quota?” then “what can I ask for?”
  • Trial: 14 days, 100 lookups/day, 20/min, one per device and AI client
  • Paid: Stripe Checkout on /pricing. After pay you land on /dash with the connect URL and (if new) the nj_ secret.

What does not exist:

  • User accounts — the token is the identity. /dash is the post-checkout install screen, not a product console.
  • Scrape-on-demand, probe, or delete watches from the catalog. Watching a competitor’s ads and units is paid only, and create is capped.

First asks

  1. “What’s my plan and remaining quota?” — does not meter.
  2. “What can I ask for?” — pick a job.
  3. “Look up gruntstyle” if you only have a brand. Do not invent a domain.
  4. Then the job: diligence on a store, a list with emails, who sells a product.

Missing catalog store → not_found. That is final. Neonjelly does not queue a scrape.