shopify

shopify

Enables AI agents to read and write Shopify store data including products, orders, customers, inventory, and more via the Admin GraphQL API.

Category
Visit Server

README

@aiwerk/mcp-server-shopify

Shopify Admin GraphQL API MCP server. Lets an AI agent read and write to a Shopify store: products, orders, customers, inventory, draft orders, collections, locations, metafields.

Built and signed by AIWerk. MIT licensed.

Status

v0.1.0 — under active development. Tool surface and credential flow may change before v1.0.

Install

npx -y @aiwerk/mcp-server-shopify

Authentication

This server uses the modern OAuth client_credentials grant (Shopify Dev Dashboard apps). Legacy shpat_* custom-app tokens are not supported.

Three environment variables:

Env var What
SHOPIFY_STORE_DOMAIN Your store domain, e.g. your-store.myshopify.com
SHOPIFY_CLIENT_ID Client ID from your Shopify Dev Dashboard app
SHOPIFY_CLIENT_SECRET Client Secret from your Shopify Dev Dashboard app

The server automatically exchanges the client credentials for an Admin API access token and refreshes the token before its 24h expiry. No manual token rotation.

Creating the Dev Dashboard app

  1. Sign in to Shopify Partner Dashboard, then open the Dev Dashboard.
  2. Apps → Create app → Start from Dev Dashboard. Name it (e.g. my-mcp-app).
  3. Versions tab → set the scopes you need (see below) → Release.
  4. Home tab → Install app → choose your store → Install.
  5. Settings tab → copy Client ID and Client Secret.

Scopes

The 12 scopes below cover the full v0.1 tool surface. Trim to a smaller set if you want a more restricted token (e.g. read-only orders).

read_products, write_products,
read_customers, write_customers,
read_orders, write_orders,
read_draft_orders, write_draft_orders,
read_inventory, write_inventory,
read_locations,
read_publications

Tools

v0.1 ships 28 tools across the Shopify Admin GraphQL API. See src/tools/ for the implementation; tool names are shown in tools/list after the server starts.

Protected customer data

Shopify gates access to customer-bearing objects (Customer, DraftOrder, plus customer { ... } selections inside Order) behind a separate approval. Apps not approved for protected customer data will see this error from the affected tools:

GraphQL error: This app is not approved to access the Customer object.
See https://shopify.dev/docs/apps/launch/protected-customer-data

The server returns this error verbatim to the AI client. Apply for protected-data approval at the link above if you need:

  • shopify_list_customers, _get_customer, _search_customers, _create_customer, _update_customer, _add_customer_note
  • shopify_create_draft_order, _complete_draft_order
  • shopify_get_order, _list_orders, _search_orders, _mark_order_paid, _cancel_order, _add_order_note (these may also be affected when the response includes customer fields)

Product, inventory, location, collection, metafield, and shop-info tools are unaffected.

API version

The server pins the Shopify GraphQL Admin API to 2026-04. Bumped quarterly per the Shopify release schedule.

Local development

npm install
npm run build

export SHOPIFY_STORE_DOMAIN=your-store.myshopify.com
export SHOPIFY_CLIENT_ID=YOUR_CLIENT_ID
export SHOPIFY_CLIENT_SECRET=YOUR_CLIENT_SECRET
node dist/src/server.js

Pull the secrets from your preferred secret store however you like. For example, with pass(1):

SHOPIFY_CLIENT_ID=$(pass show aiwerk/shopify-dev-client-id)
SHOPIFY_CLIENT_SECRET=$(pass show aiwerk/shopify-dev-client-secret)
export SHOPIFY_CLIENT_ID SHOPIFY_CLIENT_SECRET

Tests

npm test

Unit tests use mocked GraphQL responses and run with no external dependencies. There is no live integration harness in this repo — for now we smoke-test against an internal AIWerk dev store before publish.

Security

See SECURITY.md for credential handling, scope minimization, and disclosure policy.

License

MIT, see LICENSE.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured