MCP InvestmentPortfolio

🚀 Portfolio Management MCP Server

A Model Context Protocol (MCP) server that offers tools and resources for managing and analyzing investment portfolios.

✨ Features

• Portfolio Management: Create and update portfolios containing stocks and bonds.
• Market Data: Obtain real - time stock price information and relevant news.
• Analysis: Generate comprehensive portfolio reports and performance analyses.
• Recommendation: Receive personalized investment advice based on portfolio composition.
• Visualization: Create visual representations of portfolio allocations.

📦 Installation

1. Clone this repository:

   git clone https://github.com/ikhyunAn/portfolio-manager-mcp.git
   cd portfolio-manager-mcp
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Set API keys (optional):

   export ALPHA_VANTAGE_API_KEY="your_key_here"
   export NEWS_API_KEY="your_key_here"
   

   Or create a .env file in the project root directory and store the API keys.

💻 Usage Examples

Running the Server

The server can be run in two different modes:

1. Stdio Transport (default, suitable for Claude Desktop integration):

   python main.py   # Replace the command: i.e.) python3, python3.11
   

2. SSE Transport (suitable for HTTP - based clients):

   python main.py --sse
   

Integrating with Claude Desktop

Add the server to your Claude Desktop configuration file:

{
  "mcpServers": {
    "portfolio-manager": {
      "command": "python",      // Different commands may be used
      "args": ["/path/to/portfolio-manager-mcp/main.py"],
      "env": {
        "ALPHA_VANTAGE_API_KEY": "your_key_here",
        "NEWS_API_KEY": "your_key_here"
      }
    }
  }
}

If you choose to run the server in a virtual environment, the configuration file will look like this:

{
  "mcpServers": {
    "portfolio-manager": {
      "command": "/path/to/portfolio-manager-mcp/venv/bin/python",
      "args": ["/path/to/portfolio-manager-mcp/main.py"],
      "env": {
        "PYTHONPATH": "/path/to/portfolio-manager-mcp",
        "ALPHA_VANTAGE_API_KEY": "your_key_here",
        "NEWS_API_KEY": "your_key_here"
      }
    }
  }
}

To run in a virtual environment:

# Create a virtual environment
python3 -m venv venv

# Activate the virtual environment
source venv/bin/activate  # On macOS/Linux
# Or
# venv\Scripts\activate   # On Windows

# Install dependencies
pip install -r requirements.txt

# Run the server
python3 main.py

Or use the MCP CLI for easier installation:

mcp install main.py

Example Queries

Once the server is running and connected to Claude, you can use the following example queries:

• View the current status of the portfolio: portfolio status
• Get a detailed financial report: portfolio report
• Modify the investment ratio: portfolio set_allocation equity=60 bond=40
• Add a new financial asset: portfolio add_asset ticker=TSLA name=特斯拉

📚 Documentation

Project Structure

PortfolioManagerMCP/
├── main.py          # Main program entry
├── config/         # Location for configuration files and API keys storage
│   ├── api_keys.json
│   └── settings.yaml
├── portfolio/
│   ├── models/      # Portfolio analysis models
│   │   └── portfolio_analyzer.py
│   └── views/       # User interface components
│       └── portfolio_viewer.py
└── utils/           # Utility functions
    └── data_loader.py

📄 License

MIT