MCP Server

Cursor

Introduction

Cursor is an AI coding assistant that can connect various Large Language Models (LLM) to the QuantConnect MCP Server. This page explains how to set up and use the server with the Agent in the Cursor IDE. To set up the Agent with the Cursor CLI, see Using Agent in CLI in the Cursor documentation.

Getting Started

To connect the Agent in the Cursor IDE to the QC MCP Server, follow these steps:

  1. Install and open Cursor.
  2. In the top navigation bar, click View > Extensions.
  3. In the Search Exensions in Marketplace field, enter QuantConnect.
  4. Click Install.
  5. In the primary side bar, click the QuantConnect icon in Cursor QuantConnect icon.
  6. In the Initialization Checklist panel, click Login to QuantConnect.
    7. Initialization checklist in Cursor, where you can log in to QuantConnect
  7. In the Cursor window, click Open.
    8. Pop-up that enables you to open a QC link to login to your account
  8. On the Code Extension Login page, click Grant Access.
  9. In the Select Workspace panel, click Pull Organization Workspace.
    10. Select workspace
  10. In the Pull QuantConnect Organization Workspace window, click the cloud workspace (organization) that you want to pull.
    11. Pull cloud organization
  11. In the Pull QuantConnect Organization Workspace window, create a directory to serve as the organization workspace and then click Select.
    12. Pull cloud workspace

    It takes a few minutes to create a new organization workspace directory and populate it with the the initial file structure. After the organization workspace is populated with the initial file structure, it pulls your cloud project files.

  12. Press Ctrl+Shift+P to open the Command Palette, enter Open Customize, and then press Enter.
  13. On the Customize page, click MCPs > New MCP Server > User.
  14. In the ~ / .cursor / mcp.json file that opens, add the following configuration:
    15. {
  "mcpServers": {
    "qc-mcp": {
      "url": "https://www.quantconnect.com/api/v2/mcp",
      "transport": {
        "type": "Streamable HTTP"
      }
    }
  }
}
  15. In Cursor, create a new project or open an existing one.
  16. Press Ctrl+Alt+b to chat with the agent.
  17. If the agent asks you to authenticate your QuantConnect account, click Authenticate.
    18. Pop-up that asks you to authenticate your QC account

To backtest and live trade with the local Deployment Target, install Docker Desktop. The installation process depends on if your machine uses Windows, macOS, or Linux.

Models

Cursor supports several LLMs that you can use in the Chat panel, including GPT, Claude, and Gemini. To change the model, click the model name at the bottom of the Chat panel and then click the name of the model to use.

Arrow clicking the model name in the New Chat panel of Cursor, showing the list of available models.

To view all the available models, see Models in the Cursor documentation.

Quotas

There are no quotas on the QuantConnect API, but Cursor and the LLMs have some. To view the quotas, see Pricing in the Cursor documentation and see the quotas of the model you use.

Troubleshooting

The following sections explain some issues you may encounter and how to resolve them.

Service Outages

The MCP server relies on the QuantConnect API and the client application. To check the status of the QuantConnect API, see our Status page. To check the status of Cursor, see the Cursor Status page. To check the status of the LLM, see its status page. For example, Claude users can see the Anthropic Status page.

Other Issues

For more information about troubleshooting the MCP server in Cursor, see Agent in the Cursor documentation.

Examples

The following examples demonstrate the MCP server with Cursor.

Example 1: Hello World

To test the server and client are working and connected, enter the following prompt into the Cursor chat:

> Read the open project.

The agent should call the read_open_project tool.

Example 2: Strategy Development and Deployment

This example uses the Cursor Agent to brainstorm new strategy ideas, edit files, run backtests, and deploy to paper trading.

You can also see our Videos. You can also get in touch with us via Discord.

Did you find this page helpful?

Contribute to the documentation: