stripe bg
stripe bg
QUANTCONNECT MCP SERVER

Bridge AI Agents to QuantConnect

Enable your AI to design, backtest, optimize, and live trade your quantitative trading strategies on QuantConnect — through a structured, AI-friendly interface.

QuantConnect MCP
stripe-bg
stripe bg

Getting Started

To connect Copilot in Local Platform to the QC MCP Server, follow these steps:

  • In Local Platform, install the GitHub Copilot Chat extension.
  • Press Ctrl+Shift+P to open the Command Palette, enter MCP: Open User Configuration, and then press Enter.
  • Edit the mcp.json file that opens to include the server configuration.
  • Press Ctrl+S to save the mcp.json file.
  • Create a new project or open an existing one.
  • In the top navigation bar, click View > Chat.
  • At the bottom of the Chat panel that opens, click Ask > Agent to switch to Agent mode.

For more information, see the MCP Getting Started.

COPILOT CONFIG JSON 
{
  "servers": {
    "qc-mcp": {
      "url": "http://localhost:3001/",
      "type": "http"
    }
  }
}
stripe bg

Integrate Your AI Agent

stripe bg

Built for Our Quantitative Infrastructure

Designed with the needs of professional quant teams in mind, the MCP Server delivers the reliability, flexibility, and security required for real-world trading systems.

io

Project Management

Create projects, read and update file contents, and run compilations to check project status.

model

Documentation Reference

Vector search our docs, QCAlgorithm API, and thousands of examples for LLM context.

execution

Code Analysis

Runs static API syntax analysis on your code to identify and fix project errors quickly.

backtest

Backtesting

Autonomously backtest ideas, debug runtime errors, and analyze results with your AI.

quantbook

Parameter Optimization

Have your AI abstract parameters and test project sensitivity protect from overfitting.

agents

Live Trading

Automate deployment and management of projects in our institutional live environment.

stripe bg

Integrate Your AI Agent

stripe bg
QuantConnect MCP Workflow

QC MCP Enables Powerful New LLM Workflows

The QuantConnect MCP Server empowers AI to act like a trusted team member, able to execute tasks reliably on your behalf. Try some examples below to compliment your research.

"Are there interesting new strategies being discussed online?"

Search research journals and QuantConnect discussions for recent interesting posts to create your next strategy.

"Review my live algorithms. Are there any we should stop trading?"

Fetch live algorithm results and review their performance, and perform analysis to see if any are outside of expected tolerance.

"Update my project to add downside protection for outlier events."

Analyze your project code and update it to purchase downside insurance. It will also run backtests to confirm reduced drawdown.

"Debug the last runtime error and fix the project code."

The MCP will fetch the last backtest, read it's error message, and modify the project to fix the issue, and re-run your backtest to confirm success.

stripe bg

Add MCP Agents For Your Team

stripe-bg

Built to Empower Quants

A robust, transparent, and well-supported foundation for building AI enabled quant systems with confidence.

60+ Available Tools

A complete implementation of the QuantConnect API, and new AI-coding tools crafted by QuantConnect to reduce bugs in your LLM code.

Available Tools

Fully Open Source

Transparent, auditable, and extensible code written by a team you trust. Fork, modify, or contribute to the MCP on GitHub.

Contribue

Tested and Maintained

Actively developed, tested, and supported by QuantConnect, along with CI/CD system to bring you the the latest updates.

Deploy Container