mcp/quantconnect repository overview

⁠QuantConnect MCP Server

The QuantConnect MCP Server is a bridge for AIs (such as Claude and OpenAI o3 Pro) to interact with our cloud platform. When equipped with our MCP, the AI can perform tasks on your behalf through our API such as updating projects, writing strategies, backtesting, and deploying strategies to production live-trading.

What is an MCP Server?⁠

⁠MCP Info

⁠Image Building Info

Attribute	Details
Dockerfile	https://github.com/QuantConnect/mcp-server/blob/1f0fa4e4f465bae4cffb2d69eb4701ad1ddff20c/Dockerfile⁠
Commit	1f0fa4e4f465bae4cffb2d69eb4701ad1ddff20c
Docker Image built by	Docker Inc.
Docker Scout Health Score
Verify Signature	COSIGN_REPOSITORY=mcp/signatures cosign verify mcp/quantconnect --key https://raw.githubusercontent.com/docker/keyring/refs/heads/main/public/mcp/latest.pub
Licence	Apache License 2.0

⁠Available Tools (64)

⁠Tools Details

⁠Tool: abort_optimization

Abort an optimization.

⁠Tool: authorize_connection

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

    This tool automatically opens your browser for you to complete
    the authentication flow. For the flow to work, you must be 
    logged into your QuantConnect account on the browser that opens.

⁠Tool: broadcast_live_command

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

⁠Tool: check_initialization_errors

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

This tool is read-only. It does not modify its environment.

⁠Tool: check_syntax

Check the syntax of a code.

This tool is read-only. It does not modify its environment.

⁠Tool: complete_code

Show the code completion for a specific text input.

This tool is read-only. It does not modify its environment.

⁠Tool: create_backtest

Create a new backtest request and get the backtest Id.

⁠Tool: create_compile

Asynchronously create a compile job request for a project.

⁠Tool: create_file

Add a file to a given project.

⁠Tool: create_live_algorithm

Create a live algorithm.

⁠Tool: create_live_command

Send a command to a live trading algorithm.

⁠Tool: create_optimization

Create an optimization with the specified parameters.

⁠Tool: create_project

Create a new project in your default organization.

⁠Tool: create_project_collaborator

Add a collaborator to a project.

⁠Tool: delete_backtest

Delete a backtest from a project.

⁠Tool: delete_file

Delete a file in a project.

⁠Tool: delete_object

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

⁠Tool: delete_optimization

Delete an optimization.

⁠Tool: delete_project

Delete a project.

⁠Tool: delete_project_collaborator

Remove a collaborator from a project.

⁠Tool: enhance_error_message

Show additional context and suggestions for error messages.

This tool is read-only. It does not modify its environment.

⁠Tool: estimate_optimization_time

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

This tool is read-only. It does not modify its environment.

⁠Tool: liquidate_live_algorithm

Liquidate and stop a live algorithm.

⁠Tool: list_backtests

List all the backtests for the project.

This tool is read-only. It does not modify its environment.

⁠Tool: list_live_algorithms

List all your past and current live trading deployments.

⁠Tool: list_object_store_files

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

This tool is read-only. It does not modify its environment.

⁠Tool: list_optimizations

List all the optimizations for a project.

This tool is read-only. It does not modify its environment.

⁠Tool: list_projects

List the details of all projects.

⁠Tool: lock_project_with_collaborators

Lock a project so you can edit it.

    This is necessary when the project has collaborators or when an 
    LLM is editing files on your behalf via our MCP Server.

⁠Tool: patch_file

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

⁠Tool: read_account

Read the organization account status.

⁠Tool: read_backtest

Read the results of a backtest.

This tool is read-only. It does not modify its environment.

⁠Tool: read_backtest_chart

Read a chart from a backtest.

This tool is read-only. It does not modify its environment.

⁠Tool: read_backtest_insights

Read out the insights of a backtest.

This tool is read-only. It does not modify its environment.

⁠Tool: read_backtest_orders

Read out the orders of a backtest.

This tool is read-only. It does not modify its environment.

⁠Tool: read_compile

Read a compile packet job result.

This tool is read-only. It does not modify its environment.

⁠Tool: read_file

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

This tool is read-only. It does not modify its environment.

⁠Tool: read_latest_mcp_server_version

Returns the latest version of the QC MCP Server released.

⁠Tool: read_lean_versions

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

⁠Tool: read_live_algorithm

Read details of a live algorithm.

⁠Tool: read_live_chart

Read a chart from a live algorithm.

⁠Tool: read_live_insights

Read out the insights of a live algorithm.

    The snapshot updates about every 10 minutes.

⁠Tool: read_live_logs

Get the logs of a live algorithm.

    The snapshot updates about every 5 minutes.

⁠Tool: read_live_orders

Read out the orders of a live algorithm.

    The snapshot updates about every 10 minutes.

⁠Tool: read_live_portfolio

Read out the portfolio state of a live algorithm.

    The snapshot updates about every 10 minutes.

⁠Tool: read_mcp_server_version

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

⁠Tool: read_object_properties

Get Object Store properties of a specific organization and key.

    It doesn't work if the key is a directory in the Object Store.

This tool is read-only. It does not modify its environment.

⁠Tool: read_object_store_file_download_url

Get the URL for downloading files from the Object Store.

This tool is read-only. It does not modify its environment.

⁠Tool: read_object_store_file_job_id

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

⁠Tool: read_optimization

Read an optimization.

This tool is read-only. It does not modify its environment.

⁠Tool: read_project

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

This tool is read-only. It does not modify its environment.

⁠Tool: read_project_collaborators

List all collaborators on a project.

This tool is read-only. It does not modify its environment.

⁠Tool: read_project_nodes

Read the available and selected nodes of a project.

This tool is read-only. It does not modify its environment.

⁠Tool: search_quantconnect

Search for content in QuantConnect.

This tool is read-only. It does not modify its environment.

⁠Tool: stop_live_algorithm

Stop a live algorithm.

⁠Tool: update_backtest

Update the name or note of a backtest.

⁠Tool: update_code_to_pep8

Update Python code to follow PEP8 style.

This tool is read-only. It does not modify its environment.

⁠Tool: update_file_contents

Update the contents of a file.

⁠Tool: update_file_name

Update the name of a file.

⁠Tool: update_optimization

Update the name of an optimization.

⁠Tool: update_project

Update a project's name or description.

⁠Tool: update_project_collaborator

Update collaborator information in a project.

⁠Tool: update_project_nodes

Update the active state of the given nodes to true.

    If you don't provide any nodes, all the nodes become inactive 
    and autoSelectNode is true.

⁠Tool: upload_object

Upload files to the Object Store.

⁠Use this MCP Server

{
  "mcpServers": {
    "quantconnect": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "QUANTCONNECT_USER_ID",
        "-e",
        "QUANTCONNECT_API_TOKEN",
        "-e",
        "AGENT_NAME",
        "mcp/quantconnect"
      ],
      "env": {
        "QUANTCONNECT_USER_ID": "12345678",
        "QUANTCONNECT_API_TOKEN": "61b2c3d4e5f60718293a4b5c6d7e8f90a1b2c3d4e5f60718293a4b5c6d7e8f90",
        "AGENT_NAME": "MCP Server"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?⁠