shopsavvy
Model Context Protocol (MCP) server for ShopSavvy Data API - provides product lookup, pricing, and historical data tools for AI assistants.
claude mcp add --transport stdio shopsavvy-shopsavvy-mcp-server npx @shopsavvy/mcp-server \ --env SHOPSAVVY_API_KEY="your_api_key_here"
How to use
The ShopSavvy MCP Server exposes a set of product and pricing utilities that let AI assistants query ShopSavvy's product catalog, retrieve current offers from multiple retailers, fetch historical price data, and manage automatic price monitoring schedules. Core capabilities include product_lookup and product_lookup_batch for identifying items by barcode, ASIN, URL, model number, or ShopSavvy ID; product_offers and product_offers_retailer for live pricing from various retailers; product_price_history for historical price data over a specified date range; and scheduling tools like product_schedule, product_unschedule, and scheduled_products_list to automate price monitoring. You can also inspect API usage and credits via api_usage to monitor consumption. The server is designed to be configured with your ShopSavvy Data API key and exposed to clients through MCP tooling or cloud adapters.
How to install
Prerequisites:
- Node.js and npm installed on your system
- A ShopSavvy Data API key (starts with ss_live_ or ss_test_)
Installation steps:
- Install the MCP server package from npm:
npm install @shopsavvy/mcp-server
- Set your API key as an environment variable (replace with your actual key):
export SHOPSAVVY_API_KEY="ss_live_your_key_here"
- Run the MCP server locally (via npx as described in configuration) or integrate with your MCP orchestration:
# Example to launch via npx (uses the configuration from the README)
npx @shopsavvy/mcp-server
- Optional: test with MCP CLI or inspector depending on your tooling:
npm run dev
npm run inspect
- For Claude Desktop setup, add the following to your Claude configuration (see README) and restart Claude:
{
"mcpServers": {
"shopsavvy": {
"command": "npx",
"args": [
"@shopsavvy/mcp-server"
],
"env": {
"SHOPSAVVY_API_KEY": "your_api_key_here"
}
}
}
}
Additional notes
Tips and common considerations:
- Ensure your SHOPSAVVY_API_KEY is kept secret and not checked into public repos.
- The MCP server expects the API key in the SHOPSAVVY_API_KEY environment variable; you can also provide it via a .env file for local development.
- If you update the server or dependencies, run npm install again to refresh modules.
- For rate limiting and credits, monitor via the api_usage tool and align your plan with expected traffic.
- When using in production, consider wrapping the MCP server in an orchestrated container or service with proper logging, retries, and health checks.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.