QuantConnect

v1.0.0Finance & Fintechstable

🐍 ☁️ – A Dockerized Python MCP server that bridges your local AI (e.g., Claude Desktop, etc) with the QuantConnect API—empowering you to create projects, backtest strategies, manage collaborators, and deploy live-trading workflows directly via natura

algorithmic-tradingfinancemcpquantitative-finance
Share:
75
Stars
0
Downloads
0
Weekly
0/5

What is QuantConnect?

QuantConnect is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 ☁️ – a dockerized python mcp server that bridges your local ai (e.g., claude desktop, etc) with the quantconnect api—empowering you to create projects, backtest strategies, manage collaborators, an...

🐍 ☁️ – A Dockerized Python MCP server that bridges your local AI (e.g., Claude Desktop, etc) with the QuantConnect API—empowering you to create projects, backtest strategies, manage collaborators, and deploy live-trading workflows directly via natura

This server falls under the Finance & Fintech category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🐍 ☁️ – A Dockerized Python MCP server that bridges your loca

Use Cases

Algorithmic trading strategy creation
Backtesting and live trading
Quantitative finance automation
QuantConnect

Maintainer

LicenseApache 2.0
Languagepython
Versionv1.0.0
UpdatedMay 14, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y quantconnect-mcp

Manual Installation

npx -y quantconnect-mcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use QuantConnect

The QuantConnect MCP Server is a Dockerized Python server that bridges AI assistants like Claude Desktop with the QuantConnect cloud-based algorithmic trading platform. It exposes 64 tools covering the full trading lifecycle: project and file management, backtesting, parameter optimization, live trading deployment, object storage, and code analysis utilities including syntax checking and PEP8 formatting. Quant developers use it to write, test, and deploy trading strategies entirely through natural language without leaving their AI assistant.

Prerequisites

  • Docker Desktop installed and running on your machine
  • A QuantConnect account with a valid User ID and API Token (obtainable from your profile under 'Request API Token')
  • An MCP-compatible client such as Claude Desktop
  • Sufficient QuantConnect plan credits for backtesting and live trading features
1

Pull the Docker image

Pull the official QuantConnect MCP server image from Docker Hub. Use the --platform flag if you are on an Apple Silicon Mac.

# Intel/AMD
docker pull quantconnect/mcp-server

# Apple Silicon (M-series)
docker pull --platform linux/arm64 quantconnect/mcp-server
2

Retrieve your QuantConnect credentials

Log in to quantconnect.com, navigate to your profile settings, and click 'Request API Token' to generate your QUANTCONNECT_USER_ID and QUANTCONNECT_API_TOKEN.

3

Edit Claude Desktop configuration

Open Claude Desktop and go to File > Settings > Developer > Edit Config to open claude_desktop_config.json.

4

Add the QuantConnect server block

Paste the following configuration into claude_desktop_config.json, replacing the placeholder values with your actual credentials.

{
  "mcpServers": {
    "quantconnect": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "QUANTCONNECT_USER_ID",
        "-e", "QUANTCONNECT_API_TOKEN",
        "-e", "AGENT_NAME",
        "--platform", "linux/amd64",
        "quantconnect/mcp-server"
      ],
      "env": {
        "QUANTCONNECT_USER_ID": "your_user_id",
        "QUANTCONNECT_API_TOKEN": "your_api_token",
        "AGENT_NAME": "MCP Server"
      }
    }
  }
}
5

Restart Claude Desktop

Save the configuration file and restart Claude Desktop. The QuantConnect tools will be available in your next session.

6

Verify connectivity

Ask Claude to list your QuantConnect projects to confirm the server is connected and your credentials are valid.

QuantConnect Examples

Client configuration

Complete claude_desktop_config.json entry for the QuantConnect MCP server using Docker.

{
  "mcpServers": {
    "quantconnect": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "QUANTCONNECT_USER_ID",
        "-e", "QUANTCONNECT_API_TOKEN",
        "-e", "AGENT_NAME",
        "--platform", "linux/amd64",
        "quantconnect/mcp-server"
      ],
      "env": {
        "QUANTCONNECT_USER_ID": "12345",
        "QUANTCONNECT_API_TOKEN": "abc123token",
        "AGENT_NAME": "MCP Server"
      }
    }
  }
}

Prompts to try

Use these natural language prompts to interact with QuantConnect via the 64 available tools.

- "Create a new QuantConnect project called 'Moving Average Crossover'"
- "Run a backtest on my SMA strategy for the last 2 years and show me the results"
- "List all my active backtests and their performance metrics"
- "Deploy my 'Mean Reversion' strategy to live trading"
- "Check the syntax of this Python trading algorithm and fix any PEP8 issues"

Troubleshooting QuantConnect

Docker container exits immediately with authentication error

Verify your QUANTCONNECT_USER_ID and QUANTCONNECT_API_TOKEN are correct. Log in to quantconnect.com, go to profile settings, and regenerate the API token if needed.

Platform mismatch error on Apple Silicon Mac

Change the --platform argument in your config from linux/amd64 to linux/arm64, or pull the ARM image with 'docker pull --platform linux/arm64 quantconnect/mcp-server'.

Tools are not appearing in Claude Desktop after saving config

Fully quit and relaunch Claude Desktop (not just close the window). Confirm Docker Desktop is running before launching Claude Desktop, as the server starts on demand.

Frequently Asked Questions about QuantConnect

What is QuantConnect?

QuantConnect is a Model Context Protocol (MCP) server that 🐍 ☁️ – a dockerized python mcp server that bridges your local ai (e.g., claude desktop, etc) with the quantconnect api—empowering you to create projects, backtest strategies, manage collaborators, and deploy live-trading workflows directly via natura It connects AI assistants to external tools and data sources through a standardized interface.

How do I install QuantConnect?

Install via npm with the command: npx -y quantconnect-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with QuantConnect?

QuantConnect works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is QuantConnect free to use?

Yes, QuantConnect is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Finance & Fintech MCP Servers

Explore all finance & fintech servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "quantconnect": { "command": "npx", "args": ["-y", "quantconnect-mcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use QuantConnect?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides