extension

Recommendation Engine

ecommerce

•Updated Mar 13, 2025

terminal — aerostack cli

$npx aerostack add aerostack/recommendation-engine

smart_toy

MCP

Connect Claude, Cursor, or any MCP-compatible client — then call this function by slug

① Add MCP Server

Add this once — access all Aerostack functions from your AI tool.

claude_desktop_config.json

{
  "mcpServers": {
    "aerostack": {
      "url": "https://mcp.aerostack.dev",
      "type": "http"
    }
  }
}

② Call this function

Ask your AI to use the call_function tool with this slug:

call_function

call_function({
  slug: "recommendation-engine",
  args: {}
})

Ingest your product/content catalog, log user interactions, and get AI-powered personalized recommendations.

Endpoints

Method	Path	Description
POST	/ingest-items	Vectorize catalog items via RAG
POST	/recommend	Personalized recs based on user history
POST	/similar	Find items similar to a given item
POST	/interact	Log user interaction (view/purchase/rate)
GET	/trending	Top items by interaction score
GET	/health	Status check

curl -X POST {endpoint}/recommend \
  -H "Authorization: Bearer {key}" \
  -d '{"userId":"user-123","count":5}'

upgradeVersion1.0.0

gavelLicenseMIT

languageLanguagejavascript

cloudProvidercloudflare-worker

@aerostack

Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.

deployed_code

Write a TypeScript function, deploy it to the edge, and share it with thousands of developers — in minutes.