QuantConnect

Official Python MCP server for local interactions with the QuantConnect API
  • python

64

GitHub Stars

python

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "quantconnect-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "QUANTCONNECT_USER_ID",
        "-e",
        "QUANTCONNECT_API_TOKEN",
        "-e",
        "AGENT_NAME",
        "--platform",
        "<your_platform>",
        "quantconnect/mcp-server"
      ],
      "env": {
        "AGENT_NAME": "MCP Server",
        "QUANTCONNECT_USER_ID": "<your_user_id>",
        "QUANTCONNECT_API_TOKEN": "<your_api_token>"
      }
    }
  }
}

The QuantConnect MCP Server is a bridge that lets AI agents interact with your cloud QuantConnect environment. With MCP, an AI can manage projects, write strategies, run backtests, and deploy live strategies through your API tokens in a secure, dockerized workflow.

How to use

You connect an MCP client to the server by running the MCP inside a container and pointing your client to it. The official implementation is designed to be multi‑platform and works with Docker. Use a unique agent name for each client to keep requests traceable.

How to install

Prerequisites you need before starting: Docker Desktop installed on your machine. If you plan to run on an ARM chip, ensure you use the correct platform flag when pulling or running the image.

  1. Install and open Docker Desktop.

  2. Install and open Claude Desktop.

  3. In Claude Desktop, go to File > Settings > Developer > Edit Config and add the QuantConnect MCP server configuration.

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

Additional setup commands

Claude Desktop will automatically pull the MCP server image from the container registry and connect once you restart the client.

The MCP server image can be updated by pulling the latest version from the container registry. Use the command shown here to fetch the latest image. If you are on ARM, include the platform flag when pulling.

docker pull quantconnect/mcp-server

If you have an ARM chip, add the platform option when pulling.


## Available tools

### read\_account

Read the organization account status.

### create\_project

Create a new project in your default organization.

### read\_project

List the details of a project or a set of recent projects.

### list\_projects

List the details of all projects.

### update\_project

Update a project's name or description.

### delete\_project

Delete a project.

### create\_project\_collaborator

Add a collaborator to a project.

### read\_project\_collaborators

List all collaborators on a project.

### update\_project\_collaborator

Update collaborator information in a project.

### delete\_project\_collaborator

Remove a collaborator from a project.

### lock\_project\_with\_collaborators

Lock a project so you can edit it.

### read\_project\_nodes

Read the available and selected nodes of a project.

### update\_project\_nodes

Update the active state of the given nodes to true.

### create\_compile

Asynchronously create a compile job request for a project.

### read\_compile

Read a compile packet job result.

### create\_file

Add a file to a given project.

### read\_file

Read a file from a project, or all files in the project if no file name is provided.

### update\_file\_name

Update the name of a file.

### update\_file\_contents

Update the contents of a file.

### patch\_file

Apply a patch (unified diff) to a file in a project.

### delete\_file

Delete a file in a project.

### create\_backtest

Create a new backtest request and get the backtest Id.

### read\_backtest

Read the results of a backtest.

### list\_backtests

List all the backtests for the project.

### read\_backtest\_chart

Read a chart from a backtest.

### read\_backtest\_orders

Read out the orders of a backtest.

### read\_backtest\_insights

Read out the insights of a backtest.

### update\_backtest

Update the name or note of a backtest.

### delete\_backtest

Delete a backtest from a project.

### estimate\_optimization\_time

Estimate the execution time of an optimization with the specified parameters.

### create\_optimization

Create an optimization with the specified parameters.

### read\_optimization

Read an optimization.

### list\_optimizations

List all the optimizations for a project.

### update\_optimization

Update the name of an optimization.

### abort\_optimization

Abort an optimization.

### delete\_optimization

Delete an optimization.

### authorize\_connection

Authorize an external connection with a live brokerage or data provider.

### create\_live\_algorithm

Create a live algorithm.

### read\_live\_algorithm

Read details of a live algorithm.

### list\_live\_algorithms

List all your past and current live trading deployments.

### read\_live\_chart

Read a chart from a live algorithm.

### read\_live\_logs

Get the logs of a live algorithm.

### read\_live\_portfolio

Read out the portfolio state of a live algorithm.

### read\_live\_orders

Read out the orders of a live algorithm.

### read\_live\_insights

Read out the insights of a live algorithm.

### stop\_live\_algorithm

Stop a live algorithm.

### liquidate\_live\_algorithm

Liquidate and stop a live algorithm.

### create\_live\_command

Send a command to a live trading algorithm.

### broadcast\_live\_command

Broadcast a live command to all live algorithms in an organization.

### upload\_object

Upload files to the Object Store.

### read\_object\_properties

Get Object Store properties of a specific organization and key.

### read\_object\_store\_file\_job\_id

Create a job to download files from the Object Store and then read the job Id.

### read\_object\_store\_file\_download\_url

Get the URL for downloading files from the Object Store.

### list\_object\_store\_files

List the Object Store files under a specific directory in an organization.

### delete\_object

Delete the Object Store file of a specific organization and key.

### read\_lean\_versions

Returns a list of LEAN versions with basic information for each version.

### check\_initialization\_errors

Run a backtest for a few seconds to initialize the algorithm and get inialization errors if any.

### complete\_code

Show the code completion for a specific text input.

### enhance\_error\_message

Show additional context and suggestions for error messages.

### update\_code\_to\_pep8

Update Python code to follow PEP8 style.

### check\_syntax

Check the syntax of a code.

### search\_quantconnect

Search for content in QuantConnect.

### read\_mcp\_server\_version

Returns the version of the QC MCP Server that's running.

### read\_latest\_mcp\_server\_version

Returns the latest version of the QC MCP Server released.
Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational