Enables access to Shopify store data, allowing for the retrieval and searching of products, orders, and customer profiles either directly or proxied through AIVA.
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., "@AIVA MCP Server Show me customers at high risk of churning"
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.
Model Context Protocol server for AIVA - Connect your AI coding tools to AIVA's customer intelligence and Shopify data.
AIVA MCP is a Model Context Protocol server that gives AI coding assistants (Claude, Cursor, Windsurf, etc.) direct access to:
Customer Intelligence - RFM segments, health scores, churn predictions
Subscription Data - Active subscriptions, delivery schedules, lifecycle events
Affiliate Tracking - Referral codes, commissions, leaderboards
Shopify Store Data - Products, orders, customers (proxied through AIVA)
Related MCP server: InventPay MCP Server
npm install @getaiva/mcpAdd to your MCP configuration file:
Claude Desktop (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"aiva": {
"command": "npx",
"args": ["@getaiva/mcp"],
"env": {
"AIVA_API_KEY": "your-api-key-here"
}
}
}
}Cursor (.cursor/mcp.json in your project):
{
"mcpServers": {
"aiva": {
"command": "npx",
"args": ["@getaiva/mcp"],
"env": {
"AIVA_API_KEY": "your-api-key-here"
}
}
}
}VS Code with Continue (.continue/config.json):
{
"mcpServers": [
{
"name": "aiva",
"command": "npx",
"args": ["@getaiva/mcp"],
"env": {
"AIVA_API_KEY": "your-api-key-here"
}
}
]
}Log in to your AIVA Merchant Dashboard
Go to Settings > API Keys
Create a new API key with the scopes you need
Copy the key and add it to your MCP configuration
Once connected, your AI assistant can use these tools:
Tool | Description |
| Get customer profile by ID or email |
| Search customers with filters |
| Get RFM segment breakdown |
| Get customers at risk of churning |
Tool | Description |
| Get subscription details |
| List subscriptions with filters |
| Get upcoming deliveries |
| Pause, resume, skip, swap products |
Tool | Description |
| Get affiliate details |
| List affiliates with stats |
| Get referral history |
Tool | Description |
| Search/list products |
| Get product by ID |
| List orders |
| Get Shopify customer |
Variable | Required | Description |
| Yes | Your AIVA API key |
| No | Custom API URL (default: https://api.aiva.io) |
| No | Direct Shopify access (bypasses proxy) |
| No | Your Shopify store domain |
Once configured, ask your AI assistant things like:
"Show me customers at high risk of churning"
"Get the subscription details for customer john@example.com"
"List all products in the 'dog-food' collection"
"What are our top-performing affiliates this month?"
"Find customers in the 'Champions' RFM segment"git clone https://github.com/0800tim/aiva-mcp.git
cd aiva-mcp
npm install
npm run devnpm testnpm run buildMake sure your API key is set in the env section of your MCP configuration.
Check that:
Your API key is valid
You have network access to the AIVA API
The MCP server started correctly
Set DEBUG=aiva:* environment variable for verbose logging:
{
"env": {
"AIVA_API_KEY": "your-key",
"DEBUG": "aiva:*"
}
}@getaiva/create-app - CLI to scaffold AIVA-powered apps
customer-portal-starter - Customer portal starter kit
MIT - see LICENSE for details.
Get affiliate details and stats.
Inputs: affiliateId, code.
Get customers at risk of churning, sorted by risk score.
Inputs: riskLevel, limit.
Get customer profile by ID or email. Returns customer details, RFM segment, health score, and subscription status.
Inputs: customerId, email.
Get upcoming deliveries for a customer or all subscriptions.
Inputs: customerId, days.
Get referral history for an affiliate.
Inputs: affiliateId (required), dateRange.
Get RFM (Recency, Frequency, Monetary) segment breakdown with customer counts and trends.
Inputs: dateRange.
Get subscription details by ID or customer.
Inputs: subscriptionId, customerId.
List affiliates with stats, sortable by performance.
Inputs: sortBy, status, limit.
List subscriptions with filters.
Inputs: status, productId, limit, offset.
Search customers with filters. Supports filtering by segment, subscription status, tags, and more.
Inputs: query, segment, subscriptionStatus, limit, +1 more.
Perform actions on subscriptions: pause, resume, skip, swap products.
Inputs: subscriptionId (required), action (required), newProductId, skipDate.
Get Shopify customer details.
Inputs: customerId, email.
List orders with filters.
Inputs: customerId, status, limit.
Get product details by ID or handle.
Inputs: productId, handle.
Search and list products from the connected Shopify store.
Inputs: query, collection, productType, limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 15 tools
Most tools have distinct purposes, but some potential confusion exists between aiva_get_customer and aiva_search_customers (both retrieve customer data with different approaches) and between shopify_get_product and shopify_get_products (single vs. multiple retrieval). The descriptions help clarify the differences, but agents might occasionally misselect between these pairs.
All tools follow a consistent naming pattern: prefix (aiva_ or shopify_) + verb (get, list, search, or actions) + noun. This makes the tool set predictable and easy to understand, with no deviations in style or convention.
With 15 tools, the count is well-scoped for the server's purpose of managing customer and subscription data across AIVA and Shopify. It covers multiple domains without being overwhelming, and each tool appears to serve a specific, useful function.
The tool set provides strong coverage for customer, subscription, and product data retrieval, with notable features like churn risk analysis and subscription actions. Minor gaps include no update or delete operations for customers or products, and limited write capabilities beyond subscription actions, but agents can likely work around these for most workflows.
Connect AI to store orders, products and inventory with scoped access and human approvals.
Connect e-commerce and marketing data to AI assistants via MCP.
Stop copy-pasting client context into your AI. 48 connectable providers via MCP.
Connect your AI assistant to Revensi OS agents, workflows, and business data.
