AIVA MCP Server
Connects AI coding assistants to AIVA's customer intelligence and Shopify store data for managing subscriptions, affiliate tracking, and customer analytics. It enables direct access to RFM segments, churn predictions, and product information through the Model Context Protocol.
README
AIVA MCP Server
Model Context Protocol server for AIVA - Connect your AI coding tools to AIVA's customer intelligence and Shopify data.
What is this?
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)
Quick Start
Installation
npm install @getaiva/mcp
Configuration
Add 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"
}
}
]
}
Getting Your API Key
- 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
Available Tools
Once connected, your AI assistant can use these tools:
Customer Intelligence
| Tool | Description |
|---|---|
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 |
Subscriptions
| Tool | Description |
|---|---|
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 |
Affiliates
| Tool | Description |
|---|---|
aiva_get_affiliate |
Get affiliate details |
aiva_list_affiliates |
List affiliates with stats |
aiva_get_referrals |
Get referral history |
Shopify (Proxied)
| Tool | Description |
|---|---|
shopify_get_products |
Search/list products |
shopify_get_product |
Get product by ID |
shopify_get_orders |
List orders |
shopify_get_customer |
Get Shopify customer |
Environment Variables
| Variable | Required | Description |
|---|---|---|
AIVA_API_KEY |
Yes | Your AIVA API key |
AIVA_API_URL |
No | Custom API URL (default: https://api.aiva.io) |
SHOPIFY_ACCESS_TOKEN |
No | Direct Shopify access (bypasses proxy) |
SHOPIFY_STORE |
No | Your Shopify store domain |
Example Usage
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"
Development
Running Locally
git clone https://github.com/0800tim/aiva-mcp.git
cd aiva-mcp
npm install
npm run dev
Testing
npm test
Building
npm run build
Troubleshooting
"AIVA_API_KEY not configured"
Make sure your API key is set in the env section of your MCP configuration.
"Connection refused"
Check that:
- Your API key is valid
- You have network access to the AIVA API
- The MCP server started correctly
Debug Mode
Set DEBUG=aiva:* environment variable for verbose logging:
{
"env": {
"AIVA_API_KEY": "your-key",
"DEBUG": "aiva:*"
}
}
Related Packages
@getaiva/create-app- CLI to scaffold AIVA-powered appscustomer-portal-starter- Customer portal starter kit
License
MIT - see LICENSE for details.
Support
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。