# Financial Data MCP Server

A comprehensive Model Context Protocol (MCP) server for financial data analysis, portfolio management, and automated trading recommendations.

## Features

- 📊 **Real-time Stock Data** - Uses free yfinance (Yahoo Finance) API - no API keys required
- 💼 **Portfolio Management** - Track multiple portfolios with automated analysis
- 📈 **Technical Analysis** - EMA-based trend detection and MACD charts
- 🎯 **Trading Signals** - Automated buy/sell recommendations with confidence levels
- 📧 **Email Reports** - Automated batch analysis reports with chart attachments
- 📉 **Performance Tracking** - Daily monitoring of recommendation performance
- 🤖 **MCP Integration** - Full integration with Claude Code and other MCP clients

## Architecture

### Core Components

1. **financial_mcp_server.py** - Main MCP server
   - Provides MCP tools and resources for financial analysis
   - Integrates with Claude Code
   - Real-time stock data via yfinance

2. **batch_fin_mcp_server.py** - Batch analysis engine
   - Analyzes all portfolios at once
   - Generates comprehensive reports and charts
   - Implements 4 trading scenarios based on EMA analysis

3. **email_report_script.py** - Email automation
   - Sends analysis results via email
   - Attaches charts and detailed reports
   - Saves buy recommendations for tracking

4. **daily_tracking_script.py** - Performance tracking
   - Monitors buy recommendation performance
   - Creates tracking charts
   - Generates daily performance reports

## Installation

### 1. Clone the repository
```bash
git clone https://github.com/j1c4b/finance_mcp_server.git
cd finance_mcp_server
```

### 2. Create and activate virtual environment
```bash
python3 -m venv mcp_fin_server_venv
source mcp_fin_server_venv/bin/activate  # On Windows: mcp_fin_server_venv\Scripts\activate
```

### 3. Install dependencies
```bash
pip install -r clean_requirements.txt
```

## Configuration

### Portfolio Setup

Edit `portfolio.json` to add your portfolios:

```json
{
  "tech_stocks": {
    "portfolio": "Technology Giants",
    "stock_list": ["AAPL", "GOOGL", "MSFT", "AMZN", "META"]
  },
  "dividend_portfolio": {
    "portfolio": "Dividend Champions",
    "stock_list": ["JNJ", "PG", "KO", "PEP", "MMM"]
  }
}
```

### Email Configuration (Optional)

For email reports, create `email_config.json`:

```json
{
  "smtp_server": "smtp.gmail.com",
  "smtp_port": 587,
  "sender_email": "your_email@gmail.com",
  "sender_password": "your_app_password",
  "recipient_emails": ["recipient@example.com"],
  "subject_prefix": "📊 Financial Analysis Report",
  "max_attachment_size_mb": 25
}
```

## Usage

### Running the MCP Server

```bash
source mcp_fin_server_venv/bin/activate
python3 financial_mcp_server.py
```

### Batch Analysis

Analyze all portfolios and generate reports:

```bash
python3 batch_fin_mcp_server.py
```

Results are saved to `batch_financial_charts/`

### Send Email Reports

```bash
python3 email_report_script.py
```

### Track Recommendations

```bash
python3 daily_tracking_script.py
```

Results are saved to `tracking_charts/`

## MCP Tools

The server provides these tools for Claude Code integration:

- `load_portfolio` - Load portfolio data from portfolio.json
- `analyze_portfolio` - Detailed analysis of specific portfolio
- `portfolio_performance` - Performance metrics over time
- `get_stock_info` - Comprehensive stock information
- `get_earnings_calendar` - Upcoming earnings announcements
- `get_analyst_changes` - Recent analyst upgrades/downgrades
- `generate_macd_chart` - MACD technical analysis charts
- `get_market_overview` - Major market indices status

## Trading Scenarios

The batch analyzer identifies 4 key trading scenarios:

- **Scenario A**: Price >10% above 50 EMA → **SELL** signal
- **Scenario B**: Price above 50 EMA, touched recently → **BUY** signal
- **Scenario C**: Price >5% below 50 EMA, decreasing 3+ days, above 200 EMA → **BUY** signal
- **Scenario D**: Price below 50 EMA, touched 200 EMA recently → **BUY** signal

## Technical Analysis

- **Trend Detection**: Golden Cross / Death Cross analysis
- **EMAs**: 50-day and 200-day exponential moving averages
- **MACD**: Moving Average Convergence Divergence charts
- **Volume Analysis**: Trading volume patterns
- **Confidence Scores**: Each recommendation includes confidence level

## Project Structure

```
finance_mcp_server/
├── financial_mcp_server.py      # Main MCP server
├── batch_fin_mcp_server.py      # Batch analysis engine
├── email_report_script.py       # Email automation
├── daily_tracking_script.py     # Performance tracking
├── portfolio.json               # Portfolio configuration
├── requirements.txt             # Python dependencies
├── clean_requirements.txt       # Cleaned dependencies
├── CLAUDE.md                    # AI assistant guidance
├── mcp-http-bridge/             # HTTP bridge for MCP
├── batch_financial_charts/      # Generated analysis charts
└── tracking_charts/             # Performance tracking charts
```

## Requirements

- Python 3.8+
- yfinance (free Yahoo Finance API)
- pandas, numpy, matplotlib
- MCP SDK (mcp>=1.0.0)

## Disclaimer

⚠️ **This software is for informational purposes only. It does not constitute financial advice. Always do your own research before making investment decisions.**

## License

MIT License - See LICENSE file for details

## Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

## Support

For issues and questions, please open an issue on GitHub.