shopify
MCP server for Shopify api, usable on mcp hosts such as Claude and Cursor
claude mcp add --transport stdio geli2001-shopify-mcp npx shopify-mcp --clientId <YOUR_CLIENT_ID> --clientSecret <YOUR_CLIENT_SECRET> --domain <YOUR_SHOP>.myshopify.com \ --env MYSHOPIFY_DOMAIN="your-store.myshopify.com" \ --env SHOPIFY_CLIENT_ID="Your Shopify App Client ID" \ --env SHOPIFY_API_VERSION="Default: 2026-01 (can be overridden with --apiVersion)" \ --env SHOPIFY_CLIENT_SECRET="Your Shopify App Client Secret"
How to use
This Shopify MCP server integrates with Shopify's GraphQL Admin API to manage store data via a GraphQL-enabled MCP interface. It provides tools for product, customer, and order management with built-in error handling and support for both OAuth client-credentials authentication (recommended) and static access tokens for legacy apps. After configuring the server, you can query and mutate store data through the provided MCP command set, enabling workflow automation and integration with Claude Desktop or Claude Code.
To use it, configure the shopify-mcp client with your Shopify App credentials and domain, then invoke the available tools (e.g., get-products, create-product, get-product-by-id, manage-product-variants) to perform CRUD operations on products, manage customers, and query orders. The API version can be set via the --apiVersion flag or SHOPIFY_API_VERSION environment variable to align with the Shopify GraphQL Admin API you target.
How to install
Prerequisites:
- Node.js version 18 or higher
- npm (comes with Node.js)
- Access to a Shopify store with a custom app (Client ID/Secret or Static Access Token)
Step 1: Install the package globally (optional but convenient)
npm install -g shopify-mcp
Step 2: Run the MCP server using npx (preferred in many setups)
npx shopify-mcp --clientId <YOUR_CLIENT_ID> --clientSecret <YOUR_CLIENT_SECRET> --domain <YOUR_SHOP>.myshopify.com
Step 3: Alternatively, run locally with environment variables (recommended for dev)
# Create a .env file
echo 'SHOPIFY_CLIENT_ID=<YOUR_CLIENT_ID>' > .env
echo 'SHOPIFY_CLIENT_SECRET=<YOUR_CLIENT_SECRET>' >> .env
echo 'MYSHOPIFY_DOMAIN=<YOUR_SHOP>.myshopify.com' >> .env
echo 'SHOPIFY_API_VERSION=2026-01' >> .env
# Run
npx shopify-mcp
Step 4: Verifying installation
- Check the server logs for successful authentication and API readiness
- Use the available MCP commands (e.g., get-products) to confirm connectivity
Additional notes
Tips and troubleshooting:
- Ensure you are using the shopify-mcp package, not shopify-mcp-server, to avoid environment variable errors about SHOPIFY_ACCESS_TOKEN.
- If you see token-related errors, double-check that you are passing either a valid OAuth client credential flow or a valid static access token in the correct mode (client credentials vs legacy).
- The API version is configurable via --apiVersion or SHOPIFY_API_VERSION. If not set, the default 2026-01 is used.
- For local runs, exposing credentials via a .env file is convenient but ensure this file is not committed to version control.
- The available tools (e.g., get-products, create-product, update-product, delete-product, manage-product-options, manage-product-variants) cover comprehensive product and catalog management, along with customer and order data retrieval.
- If you intend to deploy, consider setting environment-specific configs for domain, client credentials, and API version to avoid accidental credential leakage across environments.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.