AIVA

You set up a Model Context Protocol (MCP) server for AIVA to empower your AI tools with direct access to customer intelligence, subscriptions, affiliates, and Shopify data. This server runs locally or alongside your development tools and exposes a focused set of actions that your AI assistants can invoke to fetch and analyze your store data.

How to use

You connect an MCP client to the AIVA MCP Server to enable your AI coding assistants to access customer data, subscription details, affiliate activity, and proxied Shopify information. Once connected, you can ask your AI to pull customer profiles, retrieve subscription histories, check delivery schedules, review affiliate performance, or browse Shopify data as part of your coding tasks. Use natural language prompts to query the available tools and have the AI return concise results or summaries that fit into your workflow.

How to install

npm install @getaiva/mcp

Next, configure your MCP client to connect to the AIVA MCP Server. The following examples show how to add the MCP server for three popular clients. Replace the placeholder API key with your actual key.

{
  "mcpServers": {
    "aiva": {
      "command": "npx",
      "args": ["@getaiva/mcp"],
      "env": {
        "AIVA_API_KEY": "your-api-key-here"
      }
    }
  }
}

{
  "mcpServers": {
    "aiva": {
      "command": "npx",
      "args": ["@getaiva/mcp"],
      "env": {
        "AIVA_API_KEY": "your-api-key-here"
      }
    }
  }
}

{
  "mcpServers": [
    {
      "name": "aiva",
      "command": "npx",
      "args": ["@getaiva/mcp"],
      "env": {
        "AIVA_API_KEY": "your-api-key-here"
      }
    }
  ]
}

Configuration snippets for common clients

Claude Desktop, Cursor, and VS Code Continue can all connect to the MCP server using the same basic runtime setup. Add the MCP server entry to your client’s MCP configuration, ensuring the API key is provided in the environment.

For Claude Desktop, place this in your configuration file under mcpServers with the appropriate key as shown in the example.

Environment considerations

The server requires an AIVA API key for authentication. You supply this key via the AIVA_API_KEY environment variable in your MCP client configuration.

Example usage

Ask your AI assistant to: "Show me customers at high risk of churning" or "Get the subscription details for customer john@example.com" to fetch real-time insights from AIVA through the MCP server.

Development

git clone https://github.com/0800tim/aiva-mcp.git
cd aiva-mcp
npm install
npm run dev

Troubleshooting

If you encounter issues, ensure your AIVA_API_KEY is set in the MCP client configuration. If you see connection errors, verify that the API key is valid and that the MCP client can reach the AIVA API.

Notes

This MCP server configuration assumes you are connecting via local or development environments using the provided npm-based runtime.

Available tools

aiva_get_customer

Get customer profile by ID or email

aiva_search_customers

Search customers with filters

aiva_get_rfm_segments

Get RFM segment breakdown

aiva_get_churn_risk

Get customers at risk of churning

aiva_get_subscription

Get subscription details

aiva_list_subscriptions

List subscriptions with filters

aiva_get_delivery_schedule

Get upcoming deliveries

aiva_subscription_actions

Pause, resume, skip, swap products

aiva_get_affiliate

Get affiliate details

aiva_list_affiliates

List affiliates with stats

aiva_get_referrals

Get referral history

shopify_get_products

Search/list products

shopify_get_product

Get product by ID

shopify_get_orders

List orders

shopify_get_customer

Get Shopify customer