Allows managing Shopify store operations including products, orders, customers, and inventory via the Shopify Admin API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Shopify Admin Server list my recent orders with status 'open'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that exposes Shopify Admin API capabilities to LLMs like Claude.
Products: List, get, create, and update products
Orders: List, get, fulfill, and cancel orders
Customers: List and get customer details
Inventory: Get inventory levels and adjust quantities
Related MCP server: shopify
Node.js 18+
A Shopify store with Admin API access
An Admin API access token with the required scopes
Your Shopify Admin API access token needs these scopes:
read_products, write_products
read_orders, write_orders
read_customers, write_customers
read_inventory, write_inventory
read_locations
Clone this repository:
git clone https://github.com/your-org/mcp-shopify-admin.git
cd mcp-shopify-adminInstall dependencies:
npm installCreate a .env file with your Shopify credentials:
cp .env.example .envEdit .env with your store domain and access token:
SHOPIFY_STORE_DOMAIN=your-store.myshopify.com
SHOPIFY_ACCESS_TOKEN=shpat_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxAdd to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"shopify": {
"command": "node",
"args": ["path/to/mcp-shopify-admin/src/index.js"],
"env": {
"SHOPIFY_STORE_DOMAIN": "your-store.myshopify.com",
"SHOPIFY_ACCESS_TOKEN": "shpat_xxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}
}
}
}Test the server using the MCP Inspector:
npx @modelcontextprotocol/inspector node src/index.jsRun the server directly (for debugging):
npm startTool | Description | Type |
| List products with filtering and pagination | Read |
| Get detailed product info by ID | Read |
| Create a new product | Write |
| Update an existing product | Write |
Tool | Description | Type |
| List orders with status filtering | Read |
| Get detailed order info by ID | Read |
| Create fulfillment for an order | Write |
| Cancel an order | Write |
Tool | Description | Type |
| List customers with search | Read |
| Get detailed customer info by ID | Read |
Tool | Description | Type |
| Get inventory at locations | Read |
| Adjust inventory quantities | Write |
All tools support two response formats via the response_format parameter:
json (default): Structured JSON for programmatic use
markdown: Human-readable formatted output
Use shopify_list_products to show me the first 10 productsUse shopify_get_order with id "5123456789" and response_format "markdown"Use shopify_update_inventory to add 50 units to inventory item "12345" at location "67890"The server provides clear error messages for common issues:
401 Unauthorized: Check your access token
403 Forbidden: Your token may lack required scopes
429 Rate Limited: Wait before making more requests
404 Not Found: The requested resource doesn't exist
MIT
Execute a previewed collection creation. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan creation of a new collection, optionally AUTOMATED via a rule_set. Use this when Shopify refuses to convert an existing manual collection: create an automated twin, then point downstream systems at it.
Inputs: store (required), title (required), handle, rule_set, +2 more.
Preview a planned collection creation.
Inputs: operation_id (required), response_format.
Get one collection by numeric ID, full GID, or handle. Reports MANUAL vs AUTOMATED and the rule set.
Inputs: store (required), id, handle, response_format.
List collections in a store. Shows whether each collection is MANUAL (hand-picked products) or AUTOMATED (rule-based), plus its rules and product count. Only AUTOMATED collections propagate their membership to external product feeds such as the Meta catalog.
Inputs: store (required), limit, query, cursor, +1 more.
Execute a previewed collection update. Production stores require confirm_production: true. Note: Shopify may reject converting an existing manual collection to automated; if so, create a new automated collection with collection_create instead.
Inputs: operation_id (required), response_format, confirm_production.
Plan an update to a collection. The main use is converting a MANUAL collection into an AUTOMATED one by supplying a rule_set (e.g. TAG EQUALS 'or-cocktail-dresses'), which makes its membership visible to external product feeds like the Meta catalog. Staged: must be previewed then executed.
Inputs: store (required), id, title, handle, +2 more.
Preview a planned collection update, showing current vs new state.
Inputs: operation_id (required), response_format.
Get detailed information about a specific customer including their address and recent orders.
Inputs: id (required), store (required), response_format.
List customers from a Shopify store with optional search and pagination.
Inputs: store (required), limit, query, cursor, +1 more.
Execute a previewed inventory adjustment. This actually changes the inventory. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan an inventory adjustment. Creates a staged operation that must be previewed and executed.
Inputs: store (required), adjustment (required), location_id (required), inventory_item_id (required), +2 more.
Preview a planned inventory adjustment. Shows the before and after quantities.
Inputs: operation_id (required), response_format.
Get inventory levels for products at specific locations. Can filter by location, product, or SKU.
Inputs: store (required), sku, limit, cursor, +3 more.
Cancel a pending operation that has not yet been executed. This is useful if you want to discard a planned operation.
Inputs: operation_id (required), response_format.
List all pending operations that are waiting for preview or execution. Operations expire after 30 minutes if not executed.
Inputs: response_format.
Get detailed status of a specific operation including its current state, preview data, and result.
Inputs: operation_id (required), response_format.
Execute a previewed order cancellation. This actually cancels the order. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan an order cancellation. This creates a staged operation that must be previewed and executed.
Inputs: store (required), order_id (required), reason, restock, +2 more.
Preview a planned order cancellation. Shows what will happen.
Inputs: operation_id (required), response_format.
Execute a previewed order fulfillment. This marks items as shipped. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan an order fulfillment. This creates a staged operation that must be previewed and executed.
Inputs: store (required), order_id (required), tracking_url, notify_customer, +3 more.
Preview a planned order fulfillment. Shows what will be shipped.
Inputs: operation_id (required), response_format.
Get detailed information about a specific order including line items, fulfillments, and customer info.
Inputs: id (required), store (required), response_format.
List orders from a Shopify store with optional filtering by status and pagination.
Inputs: store (required), limit, cursor, status, +3 more.
Execute a previewed bulk product update. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan a bulk update of multiple products. Each product can have different updates.
Inputs: store (required), updates (required), response_format.
Preview all changes in a bulk product update operation.
Inputs: operation_id (required), response_format.
Execute a previewed product creation. This actually creates the product. Requires prior preview. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan a new product creation. This creates a staged operation that must be previewed and then executed. No changes are made until execution.
Inputs: store (required), title (required), tags, status, +5 more.
Preview a planned product creation. Shows exactly what will be created. Must be called before execution.
Inputs: operation_id (required), response_format.
Get detailed information about a specific product including variants, images, and inventory.
Inputs: id (required), store (required), response_format.
List products from a Shopify store with optional filtering and pagination.
Inputs: store (required), limit, query, cursor, +1 more.
Show which sales channels a product is published to. Useful for diagnosing products that exist in a collection but never appear on the storefront or in an external feed.
Inputs: id (required), store (required), response_format.
Execute a previewed publish. Publishing is additive — it never unpublishes a product from a channel it is already on. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan publishing one or more products to one or more sales channels. Use publication_list to get channel IDs. Staged: must be previewed then executed.
Inputs: store (required), product_ids (required), publication_ids (required), response_format.
Preview which products will change publication state, and on which channels.
Inputs: operation_id (required), response_format.
Search for products using Shopify's search syntax.
Inputs: query (required), store (required), limit, response_format.
Execute a previewed additive tag operation via Shopify's tagsAdd mutation. Existing tags are never removed. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan an ADDITIVE tag operation across products. Uses Shopify's tagsAdd mutation, which appends tags without touching existing ones — safe to run concurrently and immune to the stale-snapshot tag loss that productUpdate causes. Use this instead of product_update whenever you only need to add tags. Supply either targets (per-product tags) or product_ids + tags (same tags for all).
Inputs: store (required), tags, targets, product_ids, +1 more.
Preview an additive tag operation. Shows, per product, which tags are genuinely new versus already present.
Inputs: operation_id (required), response_format.
Execute a previewed subtractive tag operation via tagsRemove. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan a SUBTRACTIVE tag operation using Shopify's tagsRemove mutation. Removes only the named tags and leaves every other tag untouched.
Inputs: store (required), tags, targets, product_ids, +1 more.
Preview a subtractive tag operation — shows which named tags are actually present per product.
Inputs: operation_id (required), response_format.
Execute a previewed product update. Requires prior preview. Production stores require confirm_production: true.
Inputs: operation_id (required), response_format, confirm_production.
Plan a product update. Creates a staged operation that must be previewed and executed. Only provided fields will be updated.
Inputs: id (required), store (required), tags, title, +5 more.
Preview a planned product update. Shows the diff between current and new values.
Inputs: operation_id (required), response_format.
List the store's publications (sales channels) — Online Store, Facebook & Instagram, Point of Sale, etc. You need a publication ID before you can publish a product to a channel.
Inputs: store (required), limit, response_format.
List all configured Shopify stores. Use this to see available stores before performing operations. Each store has a name, environment (production/staging/development), and default status.
Inputs: response_format.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 49 tools
Each tool has a distinct purpose, and the plan/preview/execute stages are clearly separated. Even overlapping tools like product_update_plan and product_tags_add_plan are explicitly disambiguated with guidance on when to use which.
Tool names consistently follow an object_verb pattern (e.g., product_list, collection_get) and the staged operations use a uniform resource_action_plan/preview/execute suffix. The few exceptions (inventory_levels, product_publications_get) are still clear and don't break the overall pattern.
At 49 tools, the server is over twice the recommended upper bound. The plan/preview/execute triple multiplies the count, but it still results in an overwhelming surface that will be difficult for agents to navigate efficiently.
The server covers the core Shopify domains well: products, collections, orders, customers, inventory, and publications. However, it lacks common operations like product/collection deletion, customer creation/update, and order creation, which are notable gaps for a full admin surface.
Connect AI to store orders, products and inventory with scoped access and human approvals.
Shopify store analysis and product-catalog extraction as agent tools.
AI-powered commerce API for luxury skincare shopping. Enables AI agents to search products, browse collections, manage shopping carts, and generate checkout URLs for the Regenique Elegance Shopify store.
Shopify MCP Pack — wraps the Shopify Admin REST API (2024-01)
