amazon_sp_mcp

Model Context Protocol (MCP) server for Amazon Seller Central - Access sales data, inventory, returns, and reports through the Amazon SP-API

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio jay-trivedi-amazon_sp_mcp node /path/to/amazon_sp_mcp/build/index.js \
  --env SELLER_ID="<your_seller_id>" \
  --env LWA_CLIENT_ID="<your_lwa_client_id>" \
  --env MARKETPLACE_ID="<your_marketplace_id>" \
  --env AWS_ACCESS_KEY_ID="<your_aws_access_key_id>" \
  --env LWA_CLIENT_SECRET="<your_lwa_client_secret>" \
  --env LWA_REFRESH_TOKEN="<your_lwa_refresh_token>" \
  --env AWS_SECRET_ACCESS_KEY="<your_aws_secret_access_key>"

How to use

This MCP server provides AI agents access to Amazon Seller Central data via the SP-API. It exposes tools to fetch sales data, returns, inventory, listings, and various reports, enabling integrated analytics with other MCPs (e.g., Google Sheets for cost data, a database MCP for historical analytics, or Notion/Airtable MCPs for product roadmaps). To use, configure an MCP client to connect to the server entry point and invoke the available SP-API based tools through the MCP SDK, including sales, returns, inventory, listings, and reports endpoints. The server is designed for composability, so you can compose data from SP-API with external data sources to derive insights like profitability, inventory health, and listing performance across marketplaces.

How to install

Prerequisites:

Node.js 18+ and npm
An Amazon Seller Central account with SP-API access (LWA credentials, seller ID, marketplace ID)

Installation steps:

Clone the repository:

git clone <repository-url>
cd amazon_sp_mcp

Install dependencies:

npm install

Configure environment variables:

cp .env.example .env

Edit .env with your credentials (or provide them via the MCP config as shown in mcp_config).

Build the project:

npm run build

Run tests (optional but recommended):

npm run test

Start the MCP server (example):

npm run start

Additional notes

Environment and configuration tips:

Ensure your SP-API credentials (AWS keys, LWA credentials, seller and marketplace IDs) are valid and have the necessary permissions.
Maintain proper handling of rate limits in production; the server includes a rate-limiter utility to respect SP-API quotas.
When integrating with Claude Code or Claude Desktop, point the MCP client to the server entry index (build/index.js) and provide the required environment variables in the client config.
Use a .env file for local development and secure storage for production secrets.
If you update APIs or endpoints, regenerate tests and re-build to ensure compatibility.

Related MCP Servers

XActions

⚡ The Complete X/Twitter Automation Toolkit — Scrapers, MCP server for AI agents (Claude/GPT), CLI, browser scripts. No API fees. Open source. Unfollow people who don't follow back. Monitor real-time analytics. Auto follow, like, comment, scrape, without API.

mobile

A Model Context Protocol (MCP) server that provides mobile automation capabilities.

mcpdog

🐕 Universal MCP Server Manager - Configure once, manage multiple MCP servers through a single interface. Perfect for Claude Desktop, Claude Code, Cursor, Gemini CLI & AI assistants. Web dashboard, auto-detection, unified proxy layer.

obsidian

MCP server for Obsidian vault management - enables Claude and other AI assistants to read, write, search, and organize your notes

webclaw

A WebMCP-native browser agent that runs inside your real Chrome — control it from Claude, Cursor, and any MCP client

twenty-crm

A clean, GraphQL-based Model Context Protocol server for Twenty CRM. Enables natural language interactions with your CRM data through Claude and other AI assistants.