Quick Start Guide

Get your QuantConnect MCP Server up and running in under 3 minutes. Professional-grade Model Context Protocol server for seamless AI-powered algorithmic trading research and portfolio optimization.

◔
~3 min Setup Time
≡
6 Simple Steps
▸
50+ Analysis Tools
1

≡ Prerequisites

Ensure you have the required tools and accounts

◆
Python 3.12+ Required
⚡
QuantConnect LEAN Required
◈
Active QuantConnect Account with API access Required
2

⚡ Installation

Clone the repository and install dependencies

Terminal 
# Clone the repository
git clone https://github.com/taylorwilsdon/quantratic.git
cd quantratic

# Install with uv (recommended)
uv sync

# Or with pip
pip install -e .
3

◈ Set Up QuantConnect Credentials

Configure your QuantConnect API credentials

Terminal 
export QUANTCONNECT_USER_ID="your_user_id"
export QUANTCONNECT_API_TOKEN="your_api_token"
export QUANTCONNECT_ORGANIZATION_ID="your_org_id"  # Optional
1

Get Your User ID

Found in the email you received when signing up for QuantConnect

2

Get Your API Token QuantConnect Settings

Available in your QuantConnect Settings page

3

Get Your Organization ID (Optional)

Found in your organization URL: /organization/{ID}

4

▸ Launch the Server

Start the QuantConnect MCP Server

STDIO Transport (Default)

Best for MCP clients like Claude Desktop

Terminal 
python main.py

HTTP Transport

Best for web integrations and testing

Terminal 
MCP_TRANSPORT=streamable-http MCP_PORT=8000 python main.py
5

↗ Start Analyzing

Begin your algorithmic trading research

Terminal 
# Initialize research environment
await initialize_quantbook(instance_name="research")

# Add securities for analysis
await add_multiple_equities(["AAPL", "MSFT", "GOOGL", "AMZN"], resolution="Daily")

# Perform sophisticated analysis
await perform_pca_analysis(
    symbols=["AAPL", "MSFT", "GOOGL", "AMZN"],
    start_date="2023-01-01",
    end_date="2024-01-01"
)
※

This example shows basic usage. The server provides 50+ tools for comprehensive financial analysis, portfolio optimization, and backtesting.

6

§ Connect to Claude Desktop

Configure Claude Desktop to use your QuantConnect MCP Server

Claude Desktop Configuration

Add QuantConnect MCP to your Claude Desktop config

config.json:

Configuration 
{
  "mcpServers": {
    "quantconnect": {
      "command": "python",
      "args": ["/path/to/quantratic/main.py"],
      "env": {
        "QUANTCONNECT_USER_ID": "your_user_id",
        "QUANTCONNECT_API_TOKEN": "your_api_token"
      }
    }
  }
}

HTTP Mode Configuration

For HTTP transport mode

Configuration 
{
  "mcpServers": {
    "quantconnect": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "http://localhost:8000/mcp"
      ]
    }
  }
}
▸

Ready to Trade!

Your QuantConnect MCP Server is now ready for professional-grade algorithmic trading research. Start building sophisticated strategies with AI-powered financial analysis, portfolio optimization, and backtesting!

≡ API Documentation ≡ QuantConnect Docs