Shopify Python MCP Server

Shopify Python MCP Server

This is an MCP server that works with the Shopify API. By using this server, you can retrieve and manipulate Shopify product information from Claude Desktop.

function

tool

The server provides the following tools:

1. list_products : Get a list of products
   • limit : Number of items to retrieve (maximum 250, default value 50)
2. get_product : Get detailed product information
   • product_id : Product ID (required)
3. create_product : Create a new product
   • title : Product name (required)
   • body_html : Product description (HTML format)
   • vendor : Vendor name
   • product_type : Product type
   • tags : tags (comma separated)
   • status : Status (active/draft/archived)
   • variants
   • options : options
   • images : Images
4. update_product : Update a product
   • product_id : Product ID (required)
   • title : Product name
   • body_html : Product description (HTML format)
   • vendor : Vendor name
   • product_type : Product type
   • tags : tags (comma separated)
   • status : Status (active/draft/archived)
   • variants
   • options : options
   • images : Images
5. delete_product : Delete a product
   • product_id : Product ID (required)

setting

Required Environment Variables

To use this server, you must set the following environment variables:

• SHOPIFY_SHOP_URL : Your Shopify store URL (e.g. mystore.myshopify.com)
• SHOPIFY_API_KEY : Shopify Admin API key
• SHOPIFY_API_PASSWORD : Shopify Admin API password (Secret)
• SHOPIFY_API_VERSION : Shopify API version (default: 2023-10)

Claude Desktop settings

If you are using Claude Desktop, add the following settings to claude_desktop_config.json:

macOS

Configuration file location: ~/Library/Application Support/Claude/claude_desktop_config.json

How to use

To use this server with Claude Desktop, call the tool as follows:

Get product list

Get detailed product information

Creating a new product

Product Updates

Remove a product

development

Installing dependencies

debug

You can debug using MCP Inspector:

Build and publish

To prepare a package for distribution:

1. Sync dependencies and update lock files:

2. Build the package:

3. Published to PyPI:

Note: You will need to set your PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username / UV_PUBLISH_USERNAME and --password / UV_PUBLISH_PASSWORD