mcpField
E
E-commerce Sales Signals MCP

E-commerce Sales Signals MCP

Remote
github.comBusiness & Marketing1Updated 4d ago

About E-commerce Sales Signals MCP

E-commerce Sales Signals MCP bundles hosted tools for sales-related data from Amazon, eBay, TikTok Shop, and Etsy. It serves product researchers, resellers, brands, and analysts through Apify's remote MCP gateway, with a local proxy option.

Key features

  1. 01Amazon bestseller ranks and reviews
  2. 02Confirmed eBay sold prices
  3. 03TikTok Shop sales estimates
  4. 04Etsy shop sales counters and search results
  5. 05Hosted gateway and local stdio proxy

Use cases

  1. 01Compare bestseller rankings across categories
  2. 02Check recent sold prices for resale research
  3. 03Track reviews or shop sales over time
  4. 04Find Etsy listings by rank and badges

MCP support

The hosted Apify gateway exposes the listed marketplace Actors as MCP tools over Streamable HTTP. An optional local stdio server lists tool schemas and forwards calls to the gateway using an Apify token.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.apify.com/?tools=junglee/amazon-bestsellers,junglee/amazon-reviews-scraper,caffein.dev/ebay-sold-listings,unseenuser/TikTok-Shop-Scraper,publicrecords/etsy-shop-velocity,publicrecords/etsy-search-scraper
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
pypiecommerce-sales-mcp0.2.1

Tools

Details

From the project README

E-commerce Sales Signals MCP: Amazon bestsellers, eBay sold prices, TikTok Shop, Etsy shop sales

What is actually selling, as MCP tools: Amazon Best Sellers ranks, Amazon reviews, confirmed eBay sold prices, TikTok Shop sales estimates and Etsy shop sales counters, in one hosted bundle. One Actor per sales signal.

Hosted remote MCP server (Streamable HTTP) on Apify's MCP gateway. Client config plus a small open-source stdio proxy server. No Actor source.

Disclosure: entries marked "(maintained by us)" are Actors I maintain on Apify Store (publisher publicrecords). Every other Actor is independent, made by its own publisher and picked on merit (Store usage, ratings and recent maintenance). This repo is not affiliated with those publishers or with the sites the Actors read.

MCP endpoint

https://mcp.apify.com/?tools=junglee/amazon-bestsellers,junglee/amazon-reviews-scraper,caffein.dev/ebay-sold-listings,unseenuser/TikTok-Shop-Scraper,publicrecords/etsy-shop-velocity,publicrecords/etsy-search-scraper

Auth: sign in with Apify (OAuth) when your client prompts, or send an Apify API token as a Bearer token. Runs are billed on your own Apify account under each Actor's own Store pricing; see each Store page.

Tools

ActorStore pageMCP toolWhat it returns
Amazon Bestsellers Scraperjunglee/amazon-bestsellersjunglee--amazon-bestsellersTop 100 items in any Amazon Best Sellers category: rank, name, price, URL.
Amazon Reviews Scraperjunglee/amazon-reviews-scraperjunglee--amazon-reviews-scraperAmazon product reviews: rating, text, date, reactions and images, for review-velocity and sentiment.
eBay Sold Listings Searchcaffein.dev/ebay-sold-listingscaffein-dot-dev--ebay-sold-listingsConfirmed eBay sold prices by keyword across 8 marketplaces, with date-range filters.
TikTok Shop Scraperunseenuser/TikTok-Shop-Scraperunseenuser--TikTok-Shop-ScraperTikTok Shop products, reviews, sellers, creator affiliates and GMV/sales estimates (US, UK).
Etsy Shop Sales Tracker (maintained by us)publicrecords/etsy-shop-velocitypublicrecords--etsy-shop-velocityEtsy shop sales counters with the date each was read, so repeat reads give sales over time. One row per shop.
Etsy Search Scraper (maintained by us)publicrecords/etsy-search-scraperpublicrecords--etsy-search-scraperEtsy search results with Bestseller and Star Seller badges, review counts and search rank.

The Apify gateway also exposes helper tools to read run results (get-actor-run, get-dataset-items). Want fewer tools? Drop any Actor from the tools= list.

Who it's for

  • Product research: which items are selling now, by marketplace?
  • Resellers: what did this item actually sell for on eBay recently?
  • Brands and agencies: how fast are a competitor's reviews or shop sales growing?
  • Analysts: track bestseller ranks and sales counters over time.

Example prompts

  • List today's top 20 Amazon Best Sellers in <category> with prices.
  • What did <item> sell for on eBay in the last 30 days? Give min, median and max.
  • How many sales did these Etsy shops show today: <shop1>, <shop2>? Read again next week and give the difference.
  • Which TikTok Shop products in <category> have the highest sales estimates?

Cursor / Claude Code / any remote-MCP client

{
  "mcpServers": {
    "ecommerce-sales": {
      "url": "https://mcp.apify.com/?tools=junglee/amazon-bestsellers,junglee/amazon-reviews-scraper,caffein.dev/ebay-sold-listings,unseenuser/TikTok-Shop-Scraper,publicrecords/etsy-shop-velocity,publicrecords/etsy-search-scraper"
    }
  }
}

Claude Code:

claude mcp add --transport http ecommerce-sales "https://mcp.apify.com/?tools=junglee/amazon-bestsellers,junglee/amazon-reviews-scraper,caffein.dev/ebay-sold-listings,unseenuser/TikTok-Shop-Scraper,publicrecords/etsy-shop-velocity,publicrecords/etsy-search-scraper"

Claude Desktop (local bridge)

{
  "mcpServers": {
    "ecommerce-sales": {
      "command": "npx",
      "args": ["-y", "@apify/actors-mcp-server", "--actors", "junglee/amazon-bestsellers,junglee/amazon-reviews-scraper,caffein.dev/ebay-sold-listings,unseenuser/TikTok-Shop-Scraper,publicrecords/etsy-shop-velocity,publicrecords/etsy-search-scraper"],
      "env": { "APIFY_TOKEN": "YOUR_APIFY_TOKEN" }
    }
  }
}

Local stdio server (open source)

This repo also ships a small MCP server in src/ for clients that only run local stdio servers. It answers initialize and tools/list locally from tools.json, which is generated from each Actor's public input schema and checked for drift in CI and weekly, so any client or directory can inspect the tools with no token. tools/call is forwarded to the hosted Apify MCP endpoint above with your own APIFY_TOKEN; without a token a call returns a clear error instead of running anything. The token is only sent in the Authorization header and is never logged.

{
  "mcpServers": {
    "ecommerce-sales": {
      "command": "npx",
      "args": ["-y", "github:GeminiGeorge22/ecommerce-sales-mcp"],
      "env": { "APIFY_TOKEN": "YOUR_APIFY_TOKEN" }
    }
  }
}

Or from a clone:

git clone https://github.com/GeminiGeorge22/ecommerce-sales-mcp.git
cd ecommerce-sales-mcp && npm install
APIFY_TOKEN=YOUR_APIFY_TOKEN node src/server.js

Optional env: APIFY_ACTORS (comma-separated subset of the Actors above) and APIFY_MCP_URL (full endpoint override).

Tests run against an in-memory mock server, with no network and no token: npm test. Requires Node.js 18+.

Python (uvx/pip)

A matching Python version of this server lives in python/, built on the official mcp Python SDK: same tools, same APIFY_TOKEN, same hosted endpoint. Requires Python 3.10+.

{
  "mcpServers": {
    "ecommerce-sales": {
      "command": "uvx",
      "args": ["ecommerce-sales-mcp"],
      "env": { "APIFY_TOKEN": "YOUR_APIFY_TOKEN" }
    }
  }
}

Or with pip: pip install ecommerce-sales-mcp, then run ecommerce-sales-mcp. Python tests: cd python && pip install -e ".[test]" && env -u APIFY_TOKEN python -m pytest.

See also

Registry

Official MCP Registry name: io.github.GeminiGeorge22/ecommerce-sales-mcp

License

MIT, for this documentation, config and the proxy server code in src/. Each Actor belongs to its publisher.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.