In the competitive world of e-commerce, data is king. Amazon sellers and vendors need deep insights into their business performance to make informed decisions. While Amazon provides rich data through their Selling Partner API, extracting actionable insights often requires specialized technical knowledge or expensive third-party tools.
Today, we're excited to introduce the Amazon Data Kiosk MCP Server – a powerful new way to interact with your Amazon business data using advanced AI assistants.
What is MCP and Why Should You Care?
The Model Context Protocol (MCP) is an open protocol that allows AI assistants to access external tools and data sources. By connecting AI to your Amazon data through our MCP server, you can have natural conversations with your business data – asking questions, generating reports, and uncovering insights without writing a single line of code.
Unlike traditional dashboards or analytics platforms, the Amazon Data Kiosk MCP server lets you:
- Ask questions in plain English about your sales, traffic, and financial performance
- Generate custom reports and visualizations tailored to your specific needs
- Combine data across different Amazon domains (sales, traffic, economics, etc.)
- Get actionable recommendations based on your business trends
How the Amazon Data Kiosk MCP Server Works
The diagram above illustrates how the Amazon Data Kiosk MCP server bridges the gap between AI and your Amazon business data:
- You start a conversation with an AI assistant in an MCP-enabled client, asking questions about your Amazon business
- The MCP Client uses the MCP protocol to determine which tools are needed to answer your question
- The Amazon Data Kiosk MCP server receives tool calls from the MCP Client and:
- Uses common utilities for authentication and API handling
- Leverages specialized servers for Seller or Vendor analytics
- Employs domain-specific tools for different types of data
- Constructs appropriate GraphQL queries through the Query Builder
- The Amazon Data Kiosk API receives these queries and returns the relevant business data
- The LLM processes and analyzes the returned data to provide you with insights in natural language
This architecture allows you to interact with complex Amazon data without needing to understand GraphQL, API authentication, or data processing techniques.
What Data Can You Access?
The Amazon Data Kiosk MCP server provides comprehensive access to your business data across multiple domains:
For Amazon Sellers:
1. Sales and Traffic Data
- Daily, weekly, or monthly sales metrics
- Traffic and conversion statistics
- Product performance by ASIN, parent ASIN, or SKU
- B2B vs. general marketplace metrics
2. Economics Data
- Detailed fee breakdowns across all Amazon fee types
- Profitability analysis by product
- Cost impact analysis
- Future fee change impact previews
For Amazon Vendors:
3. Vendor Analytics
- Sourcing metrics for distributor relationships
- Manufacturing metrics for your own products
- Inventory performance and forecasting
- Shipment and order metrics
Each data domain exposes dozens of metrics that Large Language Models can analyze, compare, and visualize, giving you unprecedented insights into your Amazon business performance.
How It Works
The Amazon Data Kiosk MCP server acts as a bridge between AI assistants and the Amazon Selling Partner API:
- You connect the server to an MCP-enabled client on your Mac or Windows computer
- Authenticate with your Amazon Selling Partner API credentials
- Start asking questions about your Amazon business
User Interaction Workflow
The diagram above shows the streamlined workflow:
- User Question: You ask Claude a question about your Amazon business in natural language, such as "How were my sales last month?"
- LLM Selects Tool: Claude analyzes your question and selects the appropriate MCP tool from the available options (sales and traffic, economics, or vendor analytics).
- Parameter Gathering: Claude collects necessary parameters for the query, such as date ranges and marketplace identifiers, either from your question or by asking follow-up questions.
- Query Execution: The MCP server builds and submits a GraphQL query to the Amazon Data Kiosk API, translating your natural language request into the required technical format.
- Amazon API: The Data Kiosk API processes your request, retrieving the requested data from Amazon's systems and returning it to the MCP server.
- Results Interpretation: Claude analyzes the raw data returned from Amazon, identifying patterns, trends, and noteworthy insights.
- Presentation: Claude presents the results in a user-friendly format with visualizations, explanations, and actionable recommendations.
- Follow-up Analysis: You can ask additional questions to explore the data further, with Claude maintaining context from the previous interactions.
This simple workflow handles all the technical complexity – authentication, query construction, data processing – behind the scenes, letting you focus on the business insights that matter most. You can continue the conversation with follow-up questions, and the system will repeat this process, maintaining context from your previous interactions.
Getting Started
Setting up the Amazon Data Kiosk MCP server involves a few simple steps:
- Clone the repository from GitHub:
git clone https://github.com/amzn/selling-partner-api-samples.git
cd use-cases/amazon-data-kiosk-mcp-server
- Install dependencies and build the project:
npm install
npm run build
- Configure MCP Client to use the server (Using Claude Desktop as an example):
Edit your Claude Desktop configuration file located at:
On macOS:
~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows:
%APPDATA%\Claude\claude_desktop_config.json
Then add the server configuration:
Note: While you can add both the seller and vendor servers to your configuration, it's recommended to add only one at a time to avoid confusion for the AI model. Choose the server that matches your account type (seller or vendor).
{
"mcpServers": {
"amazon-seller-analytics": {
"command": "node",
"args": [
"/absolute/path/to/amazon-data-kiosk-mcp-server/packages/seller-server/build/index.js"
],
"env": {
"DATA_KIOSK_CLIENT_ID": "your_client_id",
"DATA_KIOSK_CLIENT_SECRET": "your_client_secret",
"DATA_KIOSK_REFRESH_TOKEN": "your_refresh_token",
"DATA_KIOSK_BASE_URL": "https://sellingpartnerapi-na.amazon.com",
"DATA_KIOSK_OAUTH_URL": "https://api.amazon.com/auth/o2/token",
"DATA_KIOSK_API_VERSION": "2023-11-15"
}
}
}
}
Make sure to replace the paths with the actual absolute paths to the built JavaScript files on your system.
Example Conversations
Here are a few examples of how you can interact with your Amazon data through an AI assistant:
Example 1: Visualizing Sales by Day and MSKU
You: "Give me sales by days and MSKU. Output in a diagram"
Claude will:
- Create a GraphQL query targeting the sales data
- Submit it to the Amazon Data Kiosk API
- Check the query status until complete
- Download and process the results
- Generate an interactive visualization showing daily sales by MSKU
- Provide insights about the data patterns
As shown in the example, Claude can identify key patterns such as:
- Which products consistently show the highest sales volume
- Weekend sales spikes across products
- Overall sales trends and growth patterns
- Relative volatility between different products
This visualization capability makes it easy to spot patterns that might be missed when looking at raw data tables.
Example 2: Fee Impact Analysis
You: "How will the FBA fee changes coming next month affect my profitability?"
AI: [Uses MCP server to run fee preview queries and analyze results]
"I've analyzed the upcoming FBA fee changes effective June 1, 2025, for your catalog:
Overall impact: Your average profit margin will decrease by approximately 1.2% across all products.
Most affected categories:
- Oversize items (>3 lbs): Average fee increase of $1.43 per unit
- Apparel: Average fee increase of $0.78 per unit
- Small standard size: Minimal impact (avg. $0.12 increase)
Top 3 products requiring attention:
- Camping Tent (B09X123Y45Z): Profit margin will decrease from 24% to 19%
- Winter Jacket (B07A987C654): Profit margin will decrease from 32% to 28%
- Desk Lamp (B09D321E456): Profit margin will decrease from 18% to 16%
Would you like me to recommend pricing adjustments to maintain your target margins?"
Example 3: Inventory Optimization
You: "Analyze my inventory health and identify potential issues."
AI: [Uses MCP server to query inventory metrics and perform analysis]
"Based on your current inventory data, here's my analysis:
Overall inventory health score: 82/100 (Good, but with room for improvement)
Key findings:
- 72% of your inventory is selling within expected timeframes
- 18% of inventory (23 ASINs) is aging past 90 days, representing $34,562 in capital
- 5 products are at risk of stockout within the next 7 days
- Your average sell-through rate is 18% weekly (healthy for your category)
Recommendations:
- Consider running promotions for these 5 slow-moving ASINs: [list]
- Restock these 3 fast-selling items immediately: [list]
- Review your reorder quantity for seasonal items - you're currently overstocked on summer products by 34%
Would you like me to help create a restock plan or promotion strategy for any of these items?"
Technical Architecture
The Amazon Data Kiosk MCP server is built with a modern, modular architecture:
- Node.js backend for efficient processing and API communication
- GraphQL query builder to translate natural language requests to Amazon's API format
- Authentication management to handle secure API connections
- Data processing utilities to transform raw Amazon data into actionable insights
The codebase is organized into three main packages:
- common: Shared utilities and base functionality
- seller-server: MCP server for Amazon Seller Analytics
- vendor-server: MCP server for Amazon Vendor Analytics
Get Started Today
The Amazon Data Kiosk MCP server is hosted on GitHub and runs locally on your machine, ensuring your Amazon business data remains private and secure. Whether you're a small seller looking to grow your business or an established vendor managing complex operations, this tool can help you unlock the power of AI-assisted analytics for your Amazon business.
To get started:
- Make sure you have an MCP-enabled client installed
- Get your Amazon Selling Partner API credentials ready
- Clone the GitHub repository and follow the setup instructions
- Start analyzing your Amazon data with AI!
Join our community to share feedback, report issues, or contribute to the project's development.
Transform your Amazon business intelligence today with the power of Large Languge Models and the Amazon Data Kiosk MCP server!
Note: This project is not affiliated with or endorsed by Amazon. It's an independent tool that uses the Amazon Selling Partner API in compliance with Amazon's terms of service.
