What is mcp-server-amazon CLAUDE.md?

Project instructions for developing an Amazon web-scraping server that lets AI assistants access Amazon services through a standard tool interface.

Use them when installing dependencies, building the TypeScript server, cleaning mock HTML files, or changing its scraper and browser-automation code.

They give contributors the project-specific setup, build, cleanup, architecture, and authentication requirements in one place.

mcp-server-amazon CLAUDE.md — Instructions file by rigwild

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/rigwild/mcp-server-amazon/claude-md

Clone the repo

git clone --depth 1 https://github.com/rigwild/mcp-server-amazon

Per session 628 This file is loaded in full into every session.

When invoked 628 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00628	$0.00628
Opus 5	$0.00314	$0.00314
Sonnet 5	$0.00126	$0.00126
Haiku 4.5	$0.00063	$0.00063

Measured 2d ago against content hash 4e8e3c74fa3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server-amazon CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

amazon-mcp CLAUDE.md — 91% identical, 5 lines differ
mcp-server-shopping CLAUDE.md — 86% identical, 7 lines differ

CLAUDE.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This is an Amazon MCP (Model Context Protocol) Server that enables AI assistants to interact with Amazon services through web scraping. The server uses Puppeteer for browser automation and exposes Amazon functionality through MCP tools.

Development Commands

# Install dependencies (use -D flag for Puppeteer)
npm install -D

# Build TypeScript to JavaScript
npm run build

# Clean mock HTML files
npm run clean

Architecture

Core Components

MCP Server (src/index.ts): Defines and exposes tools via the MCP protocol
Amazon Scraper (src/amazon.ts): Contains all Amazon interaction logic using Puppeteer and Cheerio
Configuration (src/config.ts): Manages server settings and paths
Browser Utils (src/utils.ts): Helper functions for Puppeteer browser automation

Key Dependencies

@modelcontextprotocol/sdk: MCP framework
puppeteer: Browser automation
cheerio: HTML parsing
zod: Schema validation

Authentication

The server requires Amazon cookies for authentication:

Export cookies from browser using a cookie export extension
Save to amazonCookies.json in project root
Format: Array of cookie objects with standard properties

Important Implementation Details

Browser Automation

Uses headless Chrome with specific flags to avoid detection
Implements user agent spoofing
Handles Amazon's anti-bot measures

Error Handling

Detects login page redirects and throws authentication errors
Implements retry logic for network failures
Provides detailed error messages for debugging

Mock Mode

Set USE_MOCK_RESPONSES=true in environment to use mock HTML files
Mock files stored in mock/ directory
Useful for development and testing without hitting Amazon

Logging

Server logs to ~/Library/Logs/Claude/mcp-server-amazon.log
Check logs for debugging authentication or scraping issues

Read the full file on GitHub · 88 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 88 lines · 628 tokens per session scan A 4e8e3c74fa3c

Subscribe to this mod's changes

mcp-server-amazon CLAUDE.md is an instructions file published in the GitHub repository rigwild/mcp-server-amazon (47 stars, last pushed 1mo ago), licensed MIT. It adds 628 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Browser automation E-commerce ai amazon claude-ai mcp mcp-server model-context-protocol

mcp-server-amazon CLAUDE.md