LABSCO SUMMARY

A research desk, not a shopping bot.

The dataset is the product: years of observations sitting behind the tools, so a question like who has held the buy box on this ASIN over the past 24 months comes back immediately instead of being scraped on demand. That also draws the boundary — answers are historical and pre-collected, which makes them consistent and citeable but not today's shelf price, and nothing here writes back to Amazon.

What it is

A hosted connector over Webotee's own Amazon research data: daily marketplace observations across 11 Amazon marketplaces plus Walmart US. You ask in plain language and the assistant picks the tool. It reads and explains only — no tool places an order or changes an Amazon listing, and no Seller Central credentials are involved; you authenticate to Webotee.

What you get

find_undercompeted_brands surfaces brands with low seller competition but real sales presence, filtered by price, seller count and sales
evaluate_asin_sourcing scores one ASIN for FBA sourcing on velocity, gating, friction, margin and brand posture, with red flags
asin_buybox_history and brand_buybox_trajectory show who has held the buy box over the observed window
brand_under_attack flags a surge in new sellers, buy-box churn or price drops on a brand
operator_top_brands and brands_in_operator_network map which sellers carry what, through shared distribution
find_underserved_niches and evaluate_category_for_private_label answer whether a category is winnable for a new brand
xmkt_pricing_compare matches an ASIN's Amazon price against Walmart
The catalog runs to 50+ research tools in total

Requirements

Nothing to install or self-host: add https://app.webotee.com/mcp as a custom connector and sign in over OAuth 2.1 in the browser — no API keys to copy. A paid Webotee plan is required, from Starter at $29/mo with a 7-day free trial; free accounts get an empty tool list and an upgrade message rather than an error. Every tool call counts against a daily allowance — 200 on Starter, 10,000 on Scout + Protect. Clients that only speak local stdio reach it through mcp-remote.

Setup effort

One command — claude mcp add --transport http webotee https://app.webotee.com/mcp

See installation options

USE CASES

01

Finding a brand to source that isn't already crowded

Filter for real sales volume with few competing sellers, seeded from a brand you already know.

find_undercompeted_brandscategory_undercompeted_brands

02

Deciding whether one ASIN is worth buying

Score it on velocity, gating, friction and margin, then check a target margin against buy-box price and fees.

evaluate_asin_sourcingasin_profit_calc

03

Watching your own brand for hijackers

Detect a surge in new sellers or buy-box churn, then see who has been winning the box.

brand_under_attackasin_buybox_history

04

Profiling a competing seller

See the brands they carry by estimated sales, and which ones they just added or dropped.

operator_top_brandsoperator_new_brandsoperator_lost_brands

52 tools

Listed in project docs. Your client may show a different list.

search_products

top_sourcing_picks

evaluate_asin_sourcing

asin_profit_calc

asin_comparables

asin_buybox_history

collect_asin_now

evaluate_brand

brand_buybox_trajectory

brand_new_asins

brand_similar

brand_under_attack

brands_gaining_sellers

brands_in_operator_network

find_undercompeted_brands

BEFORE YOU INSTALL

What to know first

Tools you get

52 tools named in the project's documentation.

Requires

A client that can reach a remote MCP server over HTTP

INSTALLATION

Connect your client

Server setup

claude mcp add

Claude Code

TERMINAL

claude mcp add --transport http webotee https://app.webotee.com/mcp

Hosted endpoint

ENDPOINT URL

https://app.webotee.com/mcp

Add this hosted endpoint to your MCP client.

MCP Clients

Claude.ai, Claude Desktop

Settings → Connectors → Add custom connector → paste https://app.webotee.com/mcp → complete the Webotee sign-in (OAuth) → approve

ChatGPT

Settings → Apps & Connectors → enable Developer Mode → Create → name it "Webotee", paste the URL, set auth to OAuth

Cursor

CURSOR · JSON

{
  "mcpServers": {
    "webotee": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.webotee.com/mcp"
      ]
    }
  }
}

VS Code

VS CODE · JSON

{
  "servers": {
    "webotee": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.webotee.com/mcp"
      ]
    }
  }
}

Webotee AI Connect — Amazon Seller Intelligence