Amazon Shopping with Claude
An MCP server for searching and buying products on Amazon.
Amazon Shopping with Claude
⚠️ This project has been discontinued and is no longer maintained. No further updates, bug fixes, or support will be provided. The repository is archived for reference only.
This integration allows you to search and buy Amazon products directly through your AI assistant. Shop Amazon's vast catalog by simply chatting with Claude!
What You Need
- Claude Desktop App - Your AI shopping assistant
- Fewsats Account - Required for secure payments (takes 2 minutes to set up)
Quick Setup Guide
Step 1: Install Claude Desktop App
- Download Claude from claude.ai/download
- Install and open the app
Step 2: Set Up Fewsats
- Go to fewsats.com and create an account
- Add a payment method (credit card, Apple Pay, or Google Pay)
- Get your API key from app.fewsats.com/api-keys
Step 3: Configure Claude
-
Find your Claude config file:
- Mac: Open Terminal and paste:
open ~/Library/Application\ Support/Claude/claude_desktop_config.json - Windows: Press Win+R, type
%APPDATA%/Claude, and openclaude_desktop_config.json
- Mac: Open Terminal and paste:
-
Add this configuration (replace YOUR_FEWSATS_API_KEY with your actual key):
{
"mcpServers": {
"Amazon": {
"command": "uvx",
"args": [
"amazon-mcp"
]
},
"Fewsats": {
"command": "env",
"args": [
"FEWSATS_API_KEY=YOUR_FEWSATS_API_KEY",
"uvx",
"fewsats-mcp"
]
}
}
}
Step 4: Install UV
UV is a small tool needed to run the Amazon integration:
- Mac: Open Terminal and run:
curl -LsSf https://astral.sh/uv/install.sh | sh - Windows: Open PowerShell as Administrator and run:
irm https://astral.sh/uv/install.ps1 | iex
Start Shopping!
That's it! Now you can chat with Claude about Amazon products. Try these:
- "Find me a coffee maker under $50"
- "I need running shoes, what do you recommend?"
- "Can you search for kids' books about dinosaurs?"
Claude will help you search, compare products, and make purchases securely through Fewsats.
Using with Cursor (For Developers)
If you're a developer using Cursor, the setup is similar. In Cursor's settings, add:
{
"mcpServers": {
"Amazon": {
"command": "uvx",
"args": [
"amazon-mcp"
]
},
"Fewsats": {
"command": "env",
"args": [
"FEWSATS_API_KEY=YOUR_FEWSATS_API_KEY",
"uvx",
"fewsats-mcp"
]
}
}
}
Security First: Policies
With Fewsats, you decide how purchases are handled:
- Custom Budget Limits: Set monthly or per-transaction spending caps
- Approval Thresholds: Auto-approve small purchases, review larger ones
- Manual Review: Option to approve every purchase before it's processed
- Purchase History: Track and review all transactions in one place
About
This integration is powered by Fewsats, providing secure payment infrastructure for AI assistants. All purchases are protected by Fewsats' buyer protection policy.
Amazon is the world's largest e-commerce platform, offering millions of products across diverse categories. With features like Prime shipping, competitive pricing, and extensive product reviews, Amazon provides a comprehensive shopping experience for customers worldwide.
Need Help?
Write to us on X or at fewsats.com for assistance with payments or general questions.
Máy chủ liên quan
AcreLens
US land due-diligence MCP — returns solar potential, groundwater depth, flood zones, and county regulations for any property address.
Meyhem
Agent-native search proxy with feedback-driven ranking. Results ranked by whether agents actually succeed with them.
Everything Search
Perform lightning-fast local file searches on Windows using the Everything Search Engine.
Everything MCP Server
MCP server for Everything (voidtools) file search
Kagi Search
Web search using the Kagi Search API
Audioscrape
Add audio search to via MCP - Search any audio in seconds
Dartpoint
Access public disclosure information for Korean companies (DART) using the dartpoint.ai API.
Nexus
Web search server that integrates Perplexity Sonar models via OpenRouter API for real-time, context-aware search with citations
Academic Paper Search
Search and retrieve academic paper information from multiple sources like Semantic Scholar and CrossRef.
Semble
Fast, accurate, local code search for agents. Indexes any local path or GitHub repo on demand in ~250ms and answers queries in ~1.5ms. Works on CPU, no API keys or external services.