MCP Server AlphaVantage

🚀 MCP Server for Stock Market Analysis

This project implements a Model Context Protocol (MCP) server for stock market analysis. It provides real-time stock price data, calculates key technical indicators such as moving averages and the Relative Strength Index (RSI), and can detect trends using the AlphaVantage API. The server can be integrated with large language models like Claude to enhance financial insights.

🚀 Quick Start

Prerequisites

To run this project, you need the following:

• Python 3.8 or higher
• MCP SDK installed
• AlphaVantage API key

Installation

Install Dependencies

Use the following command to install the required libraries:

pip install mcp-server requests

Set Environment Variables

Set your AlphaVantage API key as an environment variable:

export ALPHAVANTAGE_API_KEY=your_api_key_here

Run the MCP Server

There are multiple ways to start the MCP server. It is recommended to use the following command:

mcp-server --port 5000

This will run a web interface locally, and you can access it via your browser at http://localhost:5000.

✨ Features

• Get real-time stock data using the AlphaVantage API.
• Calculate moving averages (short-term and long-term) to analyze trends.
• Detect trend crossovers (golden cross and death cross).
• Calculate the Relative Strength Index (RSI) to determine overbought/oversold conditions.
• Expose MCP tools and resources for integration with large language models.
• Future improvements include more technical indicators, backtesting functionality, and integration with trading platforms.

📚 Documentation

Why I Created It

I developed this MCP server to simplify stock market analysis. By automating data acquisition and technical indicator calculations, it helps traders and investors make data-driven decisions. The goal is to leverage AI-assisted insights, allowing users to connect to the MCP and retrieve and analyze financial data in real-time.

How It Works

Get Real-Time Stock Data

Retrieve real-time stock data through the AlphaVantage API:

import requests

def get_stock_data(symbol):
    response = requests.get(
        f'https://www.alphavantage.co/query',
        params={
            'function': 'TIME_SERIES_INTRADAY',
            'symbol': symbol,
            'apikey': os.getenv('ALPHAVANTAGE_API_KEY')
        }
    )
    return response.json()

Calculate Moving Averages

def calculate_moving_average(prices, window_size):
    return [average(prices[i:i+window_size]) for i in range(len(prices)-window_size)]

Detect Trend Crossovers

def detect_trend_changes(data):
    # Logic to implement trend crossover detection
    pass

Calculate the Relative Strength Index (RSI)

def calculate_rsi(prices, period=14):
    # RSI calculation logic
    pass

Overbought/Oversold Conditions

• RSI > 70 → Overbought (potential sell signal).
• RSI < 30 → Oversold (potential buy signal).

Future Improvements

The MCP server can be extended with the following features:

• More technical indicators such as MACD, Bollinger Bands, etc.
• Backtesting functionality to simulate past trades and validate strategies.
• Integration with trading platforms to connect with brokers for real-time trading.

🤝 Contribution Guidelines

Contributions to the project are welcome! You can contribute by submitting pull requests or reporting issues. Let's work together to make stock market analysis more intelligent and accessible!

📞 Contact

If you have any questions or suggestions, please feel free to contact me!

🔗 LinkedIn: Syed Hasan 🤗 Hugging Face: Syed-Hasan-8503