by GeLi2001
Provides access to Shopify store data via GraphQL through an MCP server, enabling product, customer, and order management directly from compatible MCP hosts.
Enables interaction with a Shopify store’s GraphQL Admin API via an MCP server, allowing tools and agents on platforms such as Claude and Cursor to query and modify products, customers, and orders.
npx shopify-mcp
(no global install required).{
"mcpServers": {
"shopify": {
"command": "npx",
"args": [
"shopify-mcp",
"--accessToken",
"<YOUR_ACCESS_TOKEN>",
"--domain",
"<YOUR_SHOP>.myshopify.com"
]
}
}
}
.env
file with SHOPIFY_ACCESS_TOKEN
and MYSHOPIFY_DOMAIN
, then run npx shopify-mcp
.claude_desktop_config.json
under mcpServers.shopify
.Q: Which Node.js version is required? A: Node.js 16 or higher.
Q: Do I need to install the package globally?
A: No. Using npx shopify-mcp
is sufficient; a global install is optional.
Q: What scopes must the Shopify custom app have?
A: read_products
, write_products
, read_customers
, write_customers
, read_orders
, write_orders
.
Q: How do I provide credentials?
A: Either via command‑line flags (--accessToken
and --domain
) or environment variables SHOPIFY_ACCESS_TOKEN
and MYSHOPIFY_DOMAIN
.
Q: I get an error about missing SHOPIFY_ACCESS_TOKEN
.
A: Ensure you are running the correct package (shopify-mcp
) and that the token is correctly set in the environment or passed as an argument.
Q: Where can I view MCP logs for debugging?
A: tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
(macOS) or the equivalent path on Windows.
(please leave a star if you like!)
MCP Server for Shopify API, enabling interaction with store data through GraphQL API. This server provides tools for managing products, customers, orders, and more.
📦 Package Name: shopify-mcp
🚀 Command: shopify-mcp
(NOT shopify-mcp-server
)
To use this MCP server, you'll need to create a custom app in your Shopify store:
read_products
, write_products
read_customers
, write_customers
read_orders
, write_orders
Add this to your claude_desktop_config.json
:
{
"mcpServers": {
"shopify": {
"command": "npx",
"args": [
"shopify-mcp",
"--accessToken",
"<YOUR_ACCESS_TOKEN>",
"--domain",
"<YOUR_SHOP>.myshopify.com"
]
}
}
}
Locations for the Claude Desktop config file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%/Claude/claude_desktop_config.json
If you prefer to use environment variables instead of command-line arguments:
Create a .env
file with your Shopify credentials:
SHOPIFY_ACCESS_TOKEN=your_access_token
MYSHOPIFY_DOMAIN=your-store.myshopify.com
Run the server with npx:
npx shopify-mcp
If you want to install the package globally:
npm install -g shopify-mcp
Then run it:
shopify-mcp --accessToken=<YOUR_ACCESS_TOKEN> --domain=<YOUR_SHOP>.myshopify.com
⚠️ Important: If you see errors about "SHOPIFY_ACCESS_TOKEN environment variable is required" when using command-line arguments, you might have a different package installed. Make sure you're using shopify-mcp
, not shopify-mcp-server
.
get-products
searchTitle
(optional string): Filter products by titlelimit
(number): Maximum number of products to returnget-product-by-id
productId
(string): ID of the product to retrieveget-customers
searchQuery
(optional string): Filter customers by name or emaillimit
(optional number, default: 10): Maximum number of customers to returnupdate-customer
id
(string, required): Shopify customer ID (numeric ID only, like "6276879810626")firstName
(string, optional): Customer's first namelastName
(string, optional): Customer's last nameemail
(string, optional): Customer's email addressphone
(string, optional): Customer's phone numbertags
(array of strings, optional): Tags to apply to the customernote
(string, optional): Note about the customertaxExempt
(boolean, optional): Whether the customer is exempt from taxesmetafields
(array of objects, optional): Customer metafields for storing additional dataget-customer-orders
customerId
(string, required): Shopify customer ID (numeric ID only, like "6276879810626")limit
(optional number, default: 10): Maximum number of orders to returnget-orders
status
(optional string): Filter by order statuslimit
(optional number, default: 10): Maximum number of orders to returnget-order-by-id
orderId
(string, required): Full Shopify order ID (e.g., "gid://shopify/Order/6090960994370")update-order
id
(string, required): Shopify order IDtags
(array of strings, optional): New tags for the orderemail
(string, optional): Update customer emailnote
(string, optional): Order notescustomAttributes
(array of objects, optional): Custom attributes for the ordermetafields
(array of objects, optional): Order metafieldsshippingAddress
(object, optional): Shipping address informationIf you encounter issues, check Claude Desktop's MCP logs:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.log
MIT
Please log in to share your review and rating for this MCP.
{ "mcpServers": { "shopify": { "command": "npx", "args": [ "shopify-mcp", "--accessToken", "<YOUR_ACCESS_TOKEN>", "--domain", "<YOUR_SHOP>.myshopify.com" ], "env": { "SHOPIFY_ACCESS_TOKEN": "<YOUR_ACCESS_TOKEN>", "MYSHOPIFY_DOMAIN": "<YOUR_SHOP>.myshopify.com" } } } }
Explore related MCPs that share similar capabilities and solve comparable challenges
by zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
by modelcontextprotocol
Model Context Protocol Servers
by modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
by modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
by cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
by continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
by upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.