Which integrations are available for this server?

Provides tools for Shopify store operations, including tracking orders, searching products, getting recommendations, managing carts, creating checkout links, and checking shipping estimates.

How do I use Clind MCP Server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Clind MCP Server track my order #1024 for customer@example.com" 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.

Clind MCP Server

Customer-facing AI agent for Shopify store operations using the Model Context Protocol (MCP).

Features

Order Tracking: Track orders by order number + email
Product Search: Search products, get recommendations, best sellers
Cart & Checkout: Add to cart, create checkout links
Shipping: Check shipping by zipcode, get delivery estimates

Setup

Install dependencies:

npm install

Configure environment variables:

cp .env.example .env

Edit .env:

SHOPIFY_STORE_URL=your-store.myshopify.com
SHOPIFY_ACCESS_TOKEN=shpca_xxxxx
PORT=3000

Start the server:

npm start

Available Tools (11 total)

Order Tracking

Tool	Description
`track_order`	Track order by order number + email
`get_order_status`	Get simple status message with tracking

Product Discovery

Tool	Description
`search_products`	Search by name, type, or tags
`get_product_details`	Get detailed product info
`get_recommendations`	Get product recommendations
`get_best_sellers`	Get top selling products
`get_collections`	Get product collections

Cart & Checkout

Tool	Description
`add_to_cart`	Generate add-to-cart link
`create_checkout_link`	Create direct checkout link

Shipping

Tool	Description
`check_shipping`	Check shipping by zipcode
`get_shipping_zones`	Get available shipping zones

API Usage

MCP Protocol (JSON-RPC 2.0)

curl -X POST http://localhost:3000/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "search_products",
      "arguments": { "query": "mug" }
    }
  }'

REST API

curl -X POST http://localhost:3000/call \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "search_products",
    "arguments": { "query": "mug" }
  }'

Example Responses

Search Products

{
  "products": [
    {
      "id": "123",
      "title": "Paint-a-Mug Kit",
      "price": "49.00",
      "url": "https://store.com/products/paint-a-mug"
    }
  ],
  "count": 1
}

Track Order

{
  "success": true,
  "order": {
    "order_number": "1001",
    "fulfillment_status": "fulfilled",
    "tracking": [
      {
        "tracking_number": "1Z999...",
        "tracking_url": "https://..."
      }
    ]
  }
}

Check Shipping

{
  "zipcode": "90210",
  "shipping_zone": "West Coast",
  "estimated_delivery": "3-5 business days",
  "shipping_options": [
    { "name": "Standard", "estimate": "3-5 days" },
    { "name": "Express", "estimate": "1-2 days" }
  ]
}

Deployment

Deploy to Railway:

railway up

Set environment variables in Railway dashboard.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd