Amazon Seller MCP
Amazon Seller Central operations via SP-API: manage inventory, track orders, analyze sales and optimize listings.
Install
The installation steps are in the documentation below. Documentation
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
Contents
Amazon Seller Operations
AI-powered Amazon Seller Central tools for inventory management, fee calculation, and optimization via SP-API.
mcp-name: io.github.wmarceau/amazon-seller
Features
| Feature | Script | Description |
|---|---|---|
| SP-API Integration | amazon_sp_api.py | Core API with caching |
| FBA Fee Calculator | amazon_fee_calculator.py | 2026 fee structure |
| Inventory Optimizer | amazon_inventory_optimizer.py | Restock recommendations |
| OAuth Authentication | amazon_oauth_server.py | OAuth flow handling |
| MCP Server | amazon_seller_mcp.py | MCP protocol wrapper |
Directory Structure
amazon-seller/
├── src/
│ ├── amazon_sp_api.py # Core SP-API client
│ ├── amazon_fee_calculator.py # FBA fee calculations
│ ├── amazon_inventory_optimizer.py # Restock recommendations
│ ├── amazon_oauth_server.py # OAuth server
│ └── ...
├── mcp-server/
│ └── amazon_seller_mcp.py # MCP server wrapper
├── registry/
│ └── manifest.json # MCP Registry manifest
├── VERSION # Current version
├── CHANGELOG.md # Version history
├── SKILL.md # MCP tool documentation
└── README.md # This fileMCP Tools
| Tool | Description |
|---|---|
get_inventory_summary | Get FBA inventory levels |
get_orders | Get recent orders |
get_order_items | Get order line items |
get_product_details | Get product info |
calculate_fba_fees | Calculate comprehensive fees |
estimate_profit_margin | Quick profit estimation |
suggest_restock_quantities | Reorder recommendations |
analyze_sell_through_rate | Sales velocity analysis |
See SKILL.md for detailed tool documentation.
Quick Start
1. Install Dependencies
pip install python-amazon-sp-api python-dotenv mcp2. Configure Credentials
Create .env file:
AMAZON_REFRESH_TOKEN=your_refresh_token
AMAZON_LWA_APP_ID=your_client_id
AMAZON_LWA_CLIENT_SECRET=your_client_secret
AMAZON_AWS_ACCESS_KEY=your_aws_access_key
AMAZON_AWS_SECRET_KEY=your_aws_secret_key
AMAZON_ROLE_ARN=arn:aws:iam::123456789:role/your-role
AMAZON_MARKETPLACE_ID=ATVPDKIKX0DER3. Test Connection
python src/test_amazon_connection.py4. Run MCP Server
python mcp-server/amazon_seller_mcp.pyCLI Usage
Calculate Fees
python src/amazon_fee_calculator.py --asin B08XYZ123 --price 29.99 --cost 10.00Get Inventory Recommendations
python src/amazon_inventory_optimizer.py --asin B08XYZ123 --days 30Key Features
2026 Fee Structure
- FBA fulfillment fees (size-tier based)
- Monthly storage fees (seasonal rates)
- Aged inventory surcharges (12-15mo, 15+mo)
- Low inventory level fees
- GET call fee awareness (post April 2026)
Caching Layer
Aggressive caching to minimize API costs:
- Inventory: 30 min
- Orders: 15 min
- Products: 24 hours
- Fees: 24 hours
Multi-Marketplace
Supports US, CA, MX, BR, UK, DE, FR, IT, ES, NL, JP, SG, AU
Version
Current version: 1.0.0
License
MIT License
Frequently asked questions
What is Amazon Seller MCP?
Amazon Seller Central operations via SP-API: manage inventory, track orders, analyze sales and optimize listings.
How do I install Amazon Seller MCP?
Follow the installation steps in its documentation, shown on this page and in its repository.
Is Amazon Seller MCP open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains Amazon Seller MCP?
It is published by MarceauSolutions. AI.tn lists it but does not maintain or endorse it.
From the community awesome-mcp-servers lists and the project's GitHub repository. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.