amazon_search_productsLABSCO SUMMARY
Product research where the shortlist gets scored, not just listed.
Search results are the easy half. The sales estimate and the opportunity score are what let candidates be ranked inside the same conversation, instead of being exported to a spreadsheet for the margin maths.
What it is
A Node MCP server for e-commerce product research, powered by Keepa price and BSR history. It searches Amazon products, returns detail on one, estimates sales, and scores a niche 0-100 on demand, competition and margin potential, with sourcing running on to Alibaba and AliExpress.
What you get
- Amazon products searched against the criteria you set
- Full detail for a product
- Sales volume estimated from Keepa price and BSR history rather than guessed
- A 0-100 opportunity score built from demand, competition and margin potential
- A sourcing pipeline connecting Amazon, Alibaba and AliExpress
- A profit calculation covering FBA fees, shipping, PPC, refunds and ROI
Requirements
A Lumnix API key from lumnix.dev, sent as a Bearer token to the hosted endpoint — nothing to install. The free key needs no credit card but covers 10 calls a month on three Amazon search tools; the rest need a paid plan. Claude Desktop reaches the endpoint through the mcp-remote bridge, which needs Node.js.
Setup effort
Add the hosted endpoint plus a key — paste it into your client, then supply credentials
USE CASES
01
Looking for a niche worth entering
Search to your criteria, then score the candidates on demand, competition and margin.
02
Sanity-checking how well something actually sells
Take the sales estimate from Keepa history alongside the product's own detail.
03
Sizing up a competitor's listing
Read the product record properly before deciding whether the category is contestable.
04
Ranking a shortlist you already have
Score each one and put the sales estimate beside it, rather than arguing from impressions.
19 tools
Listed in project docs. Your client may show a different list.
amazon_get_product_detailsamazon_estimate_salesamazon_opportunity_scoreamazon_analyze_competitionamazon_best_sellersamazon_keyword_suggestionsamazon_price_historyamazon_bsr_historyamazon_analyze_negative_reviewsamazon_analyze_listing_qualityalibaba_search_productsalibaba_get_product_detailsalibaba_vet_supplieralibaba_match_to_amazonaliexpress_search_productsaliexpress_get_product_detailsaliexpress_analyze_supplieraliexpress_profit_calculatorBEFORE YOU INSTALL
What to know first
Tools you get
19 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
Where it runs
All 4 documented clients connect to a hosted endpoint.
INSTALLATION
Connect your client
Server setup
ENDPOINT URL
https://lumnix.dev/api/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"lumnix": {
"command": "npx",
"args": [
"mcp-remote",
"https://lumnix.dev/api/mcp",
"--header",
"Authorization: Bearer <YOUR_API_KEY>"
]
}
}
}Cursor
CURSOR · JSON
{
"mcpServers": {
"lumnix": {
"url": "https://lumnix.dev/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}Windsurf
WINDSURF · JSON
{
"mcpServers": {
"lumnix": {
"serverUrl": "https://lumnix.dev/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}Cline
CLINE · JSON
{
"mcpServers": {
"lumnix": {
"type": "streamableHttp",
"url": "https://lumnix.dev/api/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}
