AmazonSeller
MCP server from mattcoatsworth/AmazonSeller-mcp-server
claude mcp add --transport stdio mattcoatsworth-amazonseller-mcp-server npx -y amazon-sp-api-mcp-server \ --env SP_API_REGION="AWS Region for SP-API (e.g., us-east-1)" \ --env SP_API_ROLE_ARN="Your AWS Role ARN" \ --env SP_API_CLIENT_ID="Your SP-API Client ID" \ --env SP_API_CLIENT_SECRET="Your SP-API Client Secret" \ --env SP_API_REFRESH_TOKEN="Your SP-API Refresh Token" \ --env SP_API_AWS_ACCESS_KEY="Your AWS Access Key" \ --env SP_API_AWS_SECRET_KEY="Your AWS Secret Key" \ --env SP_API_MARKETPLACE_ID="Marketplace ID (e.g., ATVPDKIKX0DER)"
How to use
This MCP server provides a standardized interface to the Amazon Selling Partner API (SP-API). It exposes tools and resources to interact with authentication, catalog management, inventory, orders, reports, feeds, pricing, listings, FBA operations, and more via the MCP protocol. After starting the server, you can access its tools and endpoints through the MCP client UIs or integrated tooling that speaks the MCP protocol, enabling consistent and extensible integration with your applications. The server reads credentials from the included environment variables or a .env file, and offers a variety of SP-API capabilities such as catalog item retrieval, inventory updates, order retrieval, report generation, feed submissions, and pricing/listing management. You can use the provided MCP resources to explore and execute SP-API operations in a unified way, with documentation resources available for categories like overview, authentication, catalog, orders, inventory, reports, feeds, finance, notifications, productPricing, listings, and fba.
How to install
Prerequisites:
- Node.js 16 or higher installed on your system
- npm (comes with Node.js)
- Amazon Selling Partner API credentials (client ID/secret, refresh token, AWS keys, role ARN, marketplace ID, region)
Install and run:
-
Install the MCP server package globally via npx (no persistent install required):
npx -y amazon-sp-api-mcp-server
-
Alternatively, install locally in a project:
npm install amazon-sp-api-mcp-server npm start
-
Prepare credentials: Create a .env file in the root directory with the following values:
SP_API_CLIENT_ID=your_client_id SP_API_CLIENT_SECRET=your_client_secret SP_API_REFRESH_TOKEN=your_refresh_token SP_API_AWS_ACCESS_KEY=your_aws_access_key SP_API_AWS_SECRET_KEY=your_aws_secret_key SP_API_ROLE_ARN=your_role_arn SP_API_MARKETPLACE_ID=ATVPDKIKX0DER SP_API_REGION=us-east-1
-
Start the server:
npm start
-
For development with auto-restart (if supported by the package):
npm run dev
-
To test MCP inspector or other tooling, use the provided commands as documented by the server (see available tools in the README and the server's API/docs).
Additional notes
Tips and notes:
- Ensure your SP-API credentials are valid and have the necessary permissions for the endpoints you plan to use.
- Keep your AWS IAM role and policy aligned with the SP-API access requirements.
- The server expects a .env file or environment variables; if using containerized deployment, pass the environment variables through your container orchestration tool.
- If you encounter connectivity or authentication errors, double-check region, marketplace ID, and that the role ARN is correctly assumed by the process.
- The MCP server provides a wide range of tools (authentication, catalog, inventory, orders, reports, feeds, pricing, listings, FBA, etc.). Use the documentation resources to discover category-specific endpoints and usage patterns.
- When using npx, the package will be fetched at runtime; using a local install can be preferable for offline or stable deployments.
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.