Shopify MCP Server
Enables to manage Shopify store resources like products, orders, customers, inventory, and collections through natural language using the Shopify Admin API.
README
Shopify MCP Server
A Model Context Protocol (MCP) server for integrating with Shopify Admin API. This server provides tools to access and manage products, customers, orders, inventory, and collections from your Shopify store.
Features
- Product Management: Get, search, and filter products
- Order Management: Retrieve and filter orders by status
- Customer Management: Access and search customer information
- Inventory Tracking: Check inventory levels across locations
- Collections: Access custom and smart collections
- Pagination Support: Fetch large datasets using cursor-based pagination (up to 250 items per page)
Prerequisites
- Node.js 18 or higher
- A Shopify store with Admin API access
- Shopify app client credentials (Client ID and Client Secret)
Setup
1. Get Shopify API Credentials
As of January 1, 2026, Shopify requires using the Client Credentials Grant flow for server-to-server authentication. You need to create a custom app in your Shopify admin to get client credentials:
- Go to your Shopify admin panel
- Navigate to Settings → Apps and sales channels → Develop apps
- Click Create an app and give it a name
- Go to Configuration tab
- Under Admin API access scopes, select the scopes you need:
read_products- for product accessread_orders- for order accessread_customers- for customer accessread_inventory- for inventory levels
- Click Save to save your configuration
- Go to API credentials tab
- Copy your Client ID and Client Secret
Important: The MCP server will automatically obtain and refresh access tokens using these credentials. Access tokens are valid for 24 hours and will be automatically refreshed before expiration.
2. Install Dependencies
npm install
3. Configure Environment
Create a .env file in the root directory:
cp .env.example .env
Edit .env with your Shopify credentials:
SHOPIFY_STORE_URL=your-store.myshopify.com
SHOPIFY_CLIENT_ID=your-client-id-here
SHOPIFY_CLIENT_SECRET=your-client-secret-here
SHOPIFY_API_VERSION=2024-01
4. Build the Server
npm run build
Usage with Claude Desktop
Add this server to your Claude Desktop configuration file:
macOS
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"shopify": {
"command": "node",
"args": ["/Shopify-mcp-server/dist/index.js"],
"env": {
"SHOPIFY_STORE_URL": "your-store.myshopify.com",
"SHOPIFY_CLIENT_ID": "your-client-id-here",
"SHOPIFY_CLIENT_SECRET": "your-client-secret-here",
"SHOPIFY_API_VERSION": "2024-01"
}
}
}
}
Windows
Edit %APPDATA%\Claude\claude_desktop_config.json with similar configuration.
After adding the configuration, restart Claude Desktop.
Available Tools
Pagination
All list endpoints (get_products, get_orders, get_customers, search_products, search_customers, get_inventory_levels, get_collections) support cursor-based pagination.
How it works:
- Make an initial request without
page_info - The response includes a
paginationobject with:has_next_page: Boolean indicating if more results existhas_previous_page: Boolean indicating if previous results existnext_page_info: Cursor string to fetch the next page (if available)previous_page_info: Cursor string to fetch the previous page (if available)
- To fetch the next page, use the
next_page_infovalue in thepage_infoparameter - Repeat until
has_next_pageisfalse
Example workflow:
1. get_customers(limit: 250) → returns 250 customers + next_page_info
2. get_customers(limit: 250, page_info: "cursor_abc") → returns next 250 customers
3. Continue until has_next_page is false
Products
get_products
Retrieve products with optional filtering. Supports pagination.
Parameters:
limit(number, optional): Number of products to retrieve (max 250, default 50)page_info(string, optional): Pagination cursor from previous responsestatus(string, optional): Filter by status ("active", "archived", "draft")product_type(string, optional): Filter by product typevendor(string, optional): Filter by vendorcollection_id(string, optional): Filter by collection ID
get_product
Get detailed information about a specific product.
Parameters:
product_id(string, required): The ID of the product
search_products
Search products by title. Supports pagination.
Parameters:
query(string, required): Search query stringlimit(number, optional): Number of results (max 250, default 50)page_info(string, optional): Pagination cursor from previous response
Orders
get_orders
Retrieve orders with optional filtering. Supports pagination.
Parameters:
limit(number, optional): Number of orders (max 250, default 50)page_info(string, optional): Pagination cursor from previous responsestatus(string, optional): Filter by status ("open", "closed", "cancelled", "any")financial_status(string, optional): Filter by financial statusfulfillment_status(string, optional): Filter by fulfillment status
get_order
Get detailed information about a specific order.
Parameters:
order_id(string, required): The ID of the order
Customers
get_customers
Retrieve customers from the store. Supports pagination.
Parameters:
limit(number, optional): Number of customers (max 250, default 50)page_info(string, optional): Pagination cursor from previous response
get_customer
Get detailed information about a specific customer.
Parameters:
customer_id(string, required): The ID of the customer
search_customers
Search customers by email, name, or phone. Supports pagination.
Parameters:
query(string, required): Search query (email, name, or phone)limit(number, optional): Number of results (max 250, default 50)page_info(string, optional): Pagination cursor from previous response
Inventory
get_inventory_levels
Get inventory levels for products at specific locations.
Parameters:
inventory_item_ids(array, optional): Array of inventory item IDslocation_ids(array, optional): Array of location IDslimit(number, optional): Number of results (max 250, default 50)
Collections
get_collections
Retrieve both custom and smart collections.
Parameters:
limit(number, optional): Number of collections (max 250, default 50)
Example Queries
Once connected to Claude Desktop, you can ask questions like:
- "Show me the last 10 orders"
- "Find all products with 'beer' in the title"
- "Get customer information for customer ID 123456"
- "What are my active product collections?"
- "Show me unfulfilled orders"
- "Search for customers with email containing 'example.com'"
Development
Watch Mode
For development with auto-rebuild:
npm run dev
Testing
You can test the server directly using the MCP Inspector or by connecting it to Claude Desktop.
Security Notes
- Never commit your
.envfile or expose your client credentials - Store your Client ID and Client Secret securely
- Use appropriate API scopes - only request the permissions you need
- Rotate your client credentials if they are ever compromised
- Monitor your API usage in Shopify admin
- Access tokens are automatically managed and refreshed every 24 hours
Troubleshooting
"SHOPIFY_STORE_URL, SHOPIFY_CLIENT_ID, and SHOPIFY_CLIENT_SECRET must be set"
Make sure your .env file exists and contains valid credentials, or that environment variables are properly set in your Claude Desktop configuration.
"Failed to fetch access token"
This error occurs when the client credentials are invalid or the app doesn't have permission to access the store. Verify that:
- Your Client ID and Client Secret are correct
- The app is installed on your Shopify store
- The app has the necessary API access scopes configured
API Rate Limits
Shopify has rate limits on API requests. The server doesn't currently implement rate limiting, so be mindful of rapid successive requests.
Invalid API Version
If you encounter API version errors, update the SHOPIFY_API_VERSION in your environment to a supported version (e.g., "2024-01").
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.