MCP Server

To connect Codex to the QC MCP Server, follow these steps:

1. Install and open the Codex app.
2. Sign in with your ChatGPT account.
3. In the left navigation bar, click Plugins.

4. On the Plugins page, click Add > Add custom MCP server.

5. In the Add custom MCP server form, enter a name for the server, enter the MCP server URL (https://www.quantconnect.com/api/v2/mcp), and then click Create as a plugin.

6. In the Connect QuantConnect window, click Connect QuantConnect.


Codex opens a page in your default browser. If you sign into your QuantConnect account with a different browser, update your computer's default browser application and then repeat this step.

7. In the Authorize MCP Server form, select the organization you want to connect to and then click Authorize.

Codex supports several GPT models you can use. To change the model, click the model and reasoning control beneath the chat window, and then click the name of the model to use.

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

There are no quotas on the QuantConnect API, but the Codex has some. To view the quotas, see Pricing in the ChatGPT documentation.

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 Codex, see the OpenAI Status page.

The following examples demonstrate the MCP server with Codex.

Example 1: Hello World

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

> Read the open project.

The agent calls the read_open_project tool.