Skip to main content

​
System Requirements

Minimum Requirements

  • Python 3.8 or higher
  • 512MB RAM
  • 100MB disk space
  • Internet connection

Recommended

  • Python 3.11+
  • 1GB RAM
  • 500MB disk space
  • Stable internet connection

​
Local Development Setup

​
1. Clone the Repository

git clone https://github.com/your-org/financial-mcp-server.git
cd financial-mcp-server

python3 -m venv financial-mcp
source financial-mcp/bin/activate  # On Windows: financial-mcp\Scripts\activate

​
3. Install Dependencies

pip install -r requirements.txt

​
4. Environment Configuration

Create a .env file in the project root: 
# Required for FMP professional tools
FMP_API_KEY=your_fmp_api_key

# Server configuration
PORT=8001
HOST=0.0.0.0

# Optional: Logging level
LOG_LEVEL=INFO

# Optional: CORS settings
CORS_ORIGINS=*
Never commit your .env file to version control. Add it to .gitignore.

​
5. Verify Installation

python3 main.py
Expected output: 
🚀 Starting Enhanced Financial MCP Server
📡 MCP Protocol: http://0.0.0.0:8001/
🌐 REST API: http://0.0.0.0:8001/api/v1/
📚 API Docs: http://0.0.0.0:8001/docs
🔧 Tools Available: 32 (6 YFinance + 26 FMP)

​
Production Deployment

​
Railway Deployment

1

Connect Repository

  1. Go to Railway
  2. Create new project from GitHub repository
  3. Select your financial-mcp-server repository
2

Configure Environment Variables

In Railway dashboard:
FMP_API_KEY=your_actual_api_key
PORT=$PORT
3

Deploy

Railway automatically detects Python and uses the Procfile:
web: python main.py

​
Docker Deployment

FROM python:3.11-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

EXPOSE 8001

CMD ["python", "main.py"]

​
Heroku Deployment

1

Install Heroku CLI

# macOS
brew tap heroku/brew && brew install heroku

# Other platforms: https://devcenter.heroku.com/articles/heroku-cli
2

Create Heroku App

heroku create your-financial-mcp-server
heroku config:set FMP_API_KEY=your_actual_api_key
3

Deploy

git push heroku main

​
VPS/Cloud Server

For Ubuntu/Debian servers: 
# Update system
sudo apt update && sudo apt upgrade -y

# Install Python and dependencies
sudo apt install python3 python3-pip python3-venv nginx -y

# Clone and setup
git clone https://github.com/your-org/financial-mcp-server.git
cd financial-mcp-server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# Create systemd service
sudo nano /etc/systemd/system/financial-mcp.service

# Enable and start service
sudo systemctl enable financial-mcp
sudo systemctl start financial-mcp
sudo systemctl status financial-mcp

​
API Keys Setup

​
Financial Modeling Prep (FMP)

1

Create Account

Visit Financial Modeling Prep and create a free account
2

Get API Key

After registration, find your API key in the dashboard
3

Set Environment Variable

export FMP_API_KEY="your_actual_api_key_here"
Free Tier Limits: 250 requests/day. Upgrade to paid plans for higher limits and additional features.

​
YFinance (No API Key Required)

YFinance uses Yahoo Finance’s public data and doesn’t require an API key. However, it may be subject to rate limiting.

​
Troubleshooting

Python version conflicts:
python3 --version  # Should be 3.8+
Missing pip:
python3 -m ensurepip --upgrade
Permission errors:
pip install --user -r requirements.txt
Port already in use:
# Find process using port
lsof -i :8001

# Kill process
kill -9 <PID>

# Or use different port
export PORT=8002
Missing environment variables:
# Check current environment
env | grep FMP_API_KEY

# Set if missing
export FMP_API_KEY="your_key"
FMP API errors:
  • Verify API key is correct
  • Check rate limits (250/day for free tier)
  • Ensure internet connectivity
YFinance rate limiting:
  • This is normal behavior from Yahoo Finance
  • Server implements automatic retry logic
  • Consider upgrading to FMP paid plan for reliability

​
Health Checks

Verify your installation with these endpoints: 
curl http://localhost:8001/api/v1/health

​
Next Steps

Configuration

Customize server settings and behavior

API Reference

Explore all available endpoints

Frontend Integration

Connect your application

Troubleshooting

Common issues and solutions