# Basket Trading Strategy AI Agent Connect

> Execute deterministic basket trading by evaluating correlated asset groups against a benchmark.

## Overview
- **Category:** finance
- **Price:** Free
- **Endpoint:** https://edge.vinkius.com/vk_preview_4MklCizkNTMblRdHgsSgN8k19xf1LLgbjkKv96Pq/ai-agent-connect
- **Tags:** trading, quantitative, basket-trading, finance, algorithmic-trading

## Description

This MCP server provides a deterministic quantitative trading system that treats a group of correlated assets as a single unit. By comparing the aggregate performance of a basket against a benchmark index, it identifies high-probability trade signals. Use `calculate_basket_performance` to derive metrics like tracking error and information ratio, `evaluate_trading_signal` to determine BUY, SELL, or HOLD actions based on trend and spread, and `get_basket_composition` to inspect asset weights and correlation. It includes built-in risk management like concentration filters and stop-loss logic.

## Tools

### calculate_basket_performance
Calculates core performance metrics for the basket and the benchmark

### evaluate_trading_signal
Determines the specific trade action (BUY, SELL, HOLD)

### get_basket_composition
Provides a summary of the basket composition and its relation to the benchmark

## Prompt Examples

**Prompt:** 
```
Calculate the performance metrics for a tech basket including AAPL and MSFT against the NASDAQ.
```

**Response:** 
```
The basket return is 1.2%, the benchmark return is 0.8%, resulting in a spread of 0.4%. The tracking error is 0.05 and the information ratio is 8.0.
```

**Prompt:** 
```
Should I buy the current basket based on these returns and prices?
```

**Response:** 
```
The signal is BUY. The spread is positive and the basket is trending above its 20-day Moving Average with a correlation of 0.85.
```

**Prompt:** 
```
Show me the current composition and correlation for my trading basket.
```

**Response:** 
```
The basket consists of AAPL (25%), MSFT (25%), and GOOGL (50%). However, the signal is HOLD because GOOGL exceeds the 30% concentration limit.
```

## Frequently Asked Questions

**How does the system determine a BUY signal?**
A BUY signal is generated when the basket's spread is positive and the basket price is above its 20-day Moving Average, provided the correlation with the benchmark is above 0.8 and no single asset exceeds 30% weight.

**What is the purpose of the concentration filter?**
The concentration filter prevents excessive risk by forcing a HOLD signal if any single asset in the basket accounts for more than 30% of the total weight.

**Can I use this with Cursor or Claude Desktop?**
Yes, this MCP server can be connected to Cursor, Claude Desktop, VS Code, Windsurf, and any other MCP-compatible client via Vinkius Edge.