Investment Portfolio Manager

🚀 Portfolio Management MCP Server

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

🚀 Quick Start

The Portfolio Management MCP Server provides a set of tools and resources for managing and analyzing investment portfolios. It offers features such as portfolio creation, market data retrieval, performance analysis, and personalized investment recommendations.

✨ Features

• Portfolio Management: Create and update portfolios containing stocks and bonds.
• Market Data: Obtain real - time stock price information and related news.
• Analysis: Generate comprehensive portfolio reports and performance analyses.
• Recommendation: Receive personalized investment advice based on the 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 up API keys (optional):

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

Alternatively, create a .env file in the project root directory and store the API keys there.

💻 Usage Examples

Basic Usage

Run the Server

You can run the server in two different modes:

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

python main.py   # Alternate commands: i.e.) python3, python3.11

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

python main.py --sse

Integrate with Claude Desktop

Add the server to your Claude Desktop configuration file:

{
  "mcpServers": {
    "portfolio-manager": {
      "command": "python",      // Different commands that might 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, your 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

Advanced Usage

Example Queries

Once the server is running and connected to Claude, you can interact with it using natural language:

• "Create a portfolio with 30% AAPL, 20% MSFT, 15% AMZN, and 35% US Treasury bonds, with user ID <User_ID>."
• "How has my portfolio performed recently?"
• "Show news about the stocks in my portfolio."
• "Generate investment advice for my current portfolio."
• "Visualize the current asset allocation."

📄 License

MIT