Back to catalog
QuantConnect MCP Server
Production-ready Model Context Protocol server that provides AI integration with the QuantConnect algorithmic trading platform, enabling you to manage trading strategy development, backtesting, and live trading using natural language.
Get this MCP server
Production-ready Model Context Protocol server that provides AI integration with the QuantConnect algorithmic trading platform, enabling you to manage trading strategy development, backtesting, and live trading using natural language.
Installation
uvx (Recommended)
uvx quantconnect-mcp
uv pip
uv pip install quantconnect-mcp
pip
pip install quantconnect-mcp
One-Click Installation for Claude Desktop
1. Download quantconnect-mcp.dxt from Releases
2. Double-click the file
3. Configure in Claude Desktop Settings
HTTP Transport
MCP_TRANSPORT=streamable-http MCP_PORT=8000 uvx quantconnect-mcp
Available Tools
| Tool | Description |
|---|---|
configure_quantconnect_auth |
Configure API credentials |
validate_quantconnect_auth |
Validate credential validity |
get_auth_status |
Check authentication status |
create_project |
Create a new QuantConnect project |
read_project |
Get project details or list all projects |
update_project |
Update project name/description |
compile_project |
Compile project for backtesting |
create_file |
Create a file in a project |
read_file |
Read file(s) from a project |
update_file_content |
Update file contents |
add_equity |
Add a single equity |
add_multiple_equities |
Add multiple securities |
get_history |
Get historical price data |
perform_pca_analysis |
Principal Component Analysis |
test_cointegration |
Engle-Granger cointegration test |
Capabilities
- Full project lifecycle: Create, read, update, compile, and manage QuantConnect projects and files programmatically
- Comprehensive backtesting: Compile projects, create backtests, read detailed results, and analyze charts, orders, and insights
- Live trading management: Deploy, monitor, liquidate, and control live algorithms with comprehensive execution statistics and logging
- Historical data access: Advanced data retrieval capabilities for analyzing historical and alternative data
- Advanced analytics: Perform Principal Component Analysis (PCA), Engle-Granger cointegration tests, mean reversion analysis, and correlation studies
- Portfolio optimization: Utilize sophisticated sparse optimization with Huber risk minimization, performance calculation, and strategy benchmarking
- Universe selection: Dynamic asset screening by multiple criteria, ETF constituent analysis, and correlation-based asset selection
- Enterprise security: Secure SHA-256 authenticated API integration with QuantConnect
- High-performance core: Built with asynchronous design for concurrent data processing and responsiveness
- AI-native interface: Designed for seamless interaction via natural language in advanced AI clients
Environment Variables
Required
QUANTCONNECT_USER_ID- Your QuantConnect user ID from your registration emailQUANTCONNECT_API_TOKEN- Your API token from QuantConnect Settings
Optional
QUANTCONNECT_ORGANIZATION_ID- Your organization ID from your organization URL
Usage Examples
Add GOOGL, AMZN, and MSFT, then perform PCA analysis on them for 2023.
Are Coca-Cola (KO) and Pepsi (PEP) cointegrated? Run the test for the period from 2023 to 2024. If yes, analyze their mean reversion properties with a 20-day period.
I need to manage my QuantConnect projects. First, create a new Python project named 'My_Awesome_Strategy'. Then create a 'main.py' file in it and add this code: ...your algorithm code here.... After that, compile it and run a backtest named 'Initial Run'. When done, show me the performance results.
Deploy my compiled algorithm for live trading using Interactive Brokers paper trading. Configure the broker settings with my IB credentials, then monitor execution statistics including equity, holdings, and net profit. If the algorithm shows a loss greater than 5%, automatically liquidate all positions and stop the algorithm.
Show me all my current running live algorithms. For each one, display execution statistics, recent logs from the last 100 lines, and current portfolio holdings. If any algorithm has been running for more than 24 hours without trades, flag it for review.
Notes
The server requires QuantConnect credentials (User ID and API Token) before startup. Desktop Extensions (.dxt) are available for one-click installation in Claude Desktop, bundling the server, dependencies, and manifest for seamless setup.
