Stockmcp

🚀 Yahoo Finance Model Context Protocol (MCP) for LLaMA 3.2 3B

This repository contains an implementation of the Model Context Protocol (MCP) that integrates the Yahoo Finance API with LLaMA 3.2 3B. This MCP enables the model to access real-time financial data, stock information, and market news while retaining all the regular functionalities of LLaMA.

🚀 Quick Start

The Yahoo Finance MCP for LLaMA 3.2 3B allows the model to access external financial data sources. It enriches the model's capabilities by providing real-time stock prices, company details, historical data, and market news, all while maintaining seamless performance for non-financial queries.

✨ Features

• Real-time Stock Prices: Directly access real-time stock prices within LLaMA 3.2 3B.
• Comprehensive Company Information: Retrieve detailed company information, including industry, sector, market capitalization, etc.
• Historical Stock Data: Fetch historical stock data with customizable time periods and intervals.
• Latest Market News: Get the latest market news headlines.
• Smooth Function Enhancement: Enhance LLaMA's capabilities without interfering with non-financial queries.

📦 Installation

Prerequisites

• Python 3.8+
• Ollama - For running LLaMA 3.2 3B locally.
• LLaMA 3.2 3B model pulled via Ollama.
• Python packages:
  • ollama
  • yfinance
  • requests
  • pandas

Steps

1. Install Ollama from https://ollama.ai/.
2. Pull the LLaMA 3.2 3B model using Ollama:

ollama pull llama3.2:3b

3. Clone this repository:

git clone <repository-url>
cd mcp_yahoo_finance

4. Install the required Python dependencies:

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

Running MCP with Ollama Integration

To use the Yahoo Finance MCP with LLaMA 3.2 3B via Ollama:

python mcp_ollama_integration.py

This will start an interactive session where you can:

• Ask financial-related questions, which will be answered with enriched data from Yahoo Finance.
• Ask non-financial questions.

Command-line Options

• -h, --help: Display help information and exit.
• --port PORT: Specify the port on which the service runs. The default is 8000.

Advanced Usage

How It Works

The MCP acts as an adapter that allows LLaMA to access an external data source (Yahoo Finance). It does this by intercepting and processing queries in a specific format. When a user asks a question that requires real-time data, the MCP calls the Yahoo Finance API to obtain the latest information and returns it to the model.

Example

After installation, run the following in the terminal:

python mcp_ollama_integration.py

Then, in another terminal, run:

curl http://localhost:8000

📚 Documentation

Troubleshooting

Issue: Service Not Starting

• Check if Ollama is installed and running correctly.
• Ensure that the model has been pulled correctly.

Issue: Unable to Connect to Ollama

• Check if the Ollama service is running.
• Ensure that the firewall allows access to the relevant ports.

Issue: API Call Failure

• Check the network connection.
• Ensure that the Yahoo Finance API key is valid.

Notes

• This tool is for research and educational purposes only.
• Please read Yahoo Finance's terms of use and service agreement before use.

📄 License

Thanks to all contributors who have contributed to this project!