QuantConnect MCP Server
Provides comprehensive tools for algorithmic trading development including project management, backtesting, optimization, live trading deployment, file management, and strategy development through the QuantConnect cloud platform API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@QuantConnect MCP Server create a backtest for my momentum strategy on SPY"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Our implementation is tested and dockerized for easy cross-platform deployment.
Getting Started
To connect local MCP clients (like Claude Desktop) to the QC MCP Server, follow these steps:
Install and open Docker Desktop.
Install and open Claude Desktop.
In Claude Desktop, click File > Settings > Developer > Edit Config.
Edit the
claude_desktop_config.jsonfile to include the followingquantconnectconfiguration:
{
"mcpServers": {
"quantconnect": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e", "QUANTCONNECT_USER_ID",
"-e", "QUANTCONNECT_API_TOKEN",
"-e", "AGENT_NAME",
"--platform", "<your_platform>",
"--name",
"quantconnect-mcp-server",
"quantconnect/mcp-server"
],
"env": {
"QUANTCONNECT_USER_ID": "<your_user_id>",
"QUANTCONNECT_API_TOKEN": "<your_api_token>",
"AGENT_NAME": "MCP Server"
}
}
}
}To get your user Id and API token, see Request API Token.
Our MCP server is multi-platform capable. The options are linux/amd64 for Intel/AMD chips and linux/arm64 for ARM chips (for example, Apple's M-series chips).
If you simultaneously run multiple agents, set a unique value for the AGENT_NAME environment variable for each agent to keep record of the request source.
Restart Claude Desktop.
Claude Desktop automatically pulls our MCP server from Docker Hub and connects to it.
To view all the MCP clients and the features they support, see the Feature Support Matrix in the MCP documentation.
To keep the Docker image up-to-date, pull the latest MCP server from Docker Hub in the terminal.
docker pull quantconnect/mcp-serverIf you have an ARM chip, add the --platform linux/arm64 option.
Related MCP server: Alpaca MCP Server
Available Tools (60)
Tools provided by this Server | Short Description |
| Read the organization account status. |
| Create a new project in your default organization. |
| List the details of a project. |
| List the details of all projects. |
| Update a project's name or description. |
| Delete a project. |
| Add a collaborator to a project. |
| List all collaborators on a project. |
| Update collaborator information in a project. |
| Remove a collaborator from a project. |
| Read the available and selected nodes of a project. |
| Update the active state of the given nodes to true. |
| Asynchronously create a compile job request for a project. |
| Read a compile packet job result. |
| Add a file to a given project. |
| Read a file from a project, or all files in the project if no file name is provided. |
| Update the name of a file. |
| Update the contents of a file. |
| Delete a file in a project. |
| Create a new backtest request and get the backtest Id. |
| Read the results of a backtest. |
| List all the backtests for the project. |
| Read a chart from a backtest. |
| Read out the orders of a backtest. |
| Read out the insights of a backtest. |
| Update the name or note of a backtest. |
| Delete a backtest from a project. |
| Estimate the execution time of an optimization with the specified parameters. |
| Create an optimization with the specified parameters. |
| Read an optimization. |
| List all the optimizations for a project. |
| Update the name of an optimization. |
| Abort an optimization. |
| Delete an optimization. |
| Authorize an external connection with a live brokerage or data provider. |
| Create a live algorithm. |
| Read details of a live algorithm. |
| List all your past and current live trading deployments. |
| Read a chart from a live algorithm. |
| Get the logs of a live algorithm. |
| Read out the portfolio state of a live algorithm. |
| Read out the orders of a live algorithm. |
| Read out the insights of a live algorithm. |
| Stop a live algorithm. |
| Liquidate and stop a live algorithm. |
| Send a command to a live trading algorithm. |
| Broadcast a live command to all live algorithms in an organization. |
| Upload files to the Object Store. |
| Get Object Store properties of a specific organization and key. |
| Create a job to download files from the Object Store and then read the job Id. |
| Get the URL for downloading files from the Object Store. |
| List the Object Store files under a specific directory in an organization. |
| Delete the Object Store file of a specific organization and key. |
| Returns a list of LEAN versions with basic information for each version. |
| Run a backtest for a few seconds to initialize the algorithm and get initialization errors if any. |
| Show the code completion for a specific text input. |
| Show additional context and suggestions for error messages. |
| Update Python code to follow PEP8 style. |
| Check the syntax of a code. |
| Search for content in QuantConnect. |
Tool Details
Tool: read_account
Read the organization account status.
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: create_project
Create a new project in your default organization.
Parameter | Type | Description |
|
| Project name. |
|
| Programming language to use. |
|
| The organization to create project under. If you don't provide a value, it defaults to your preferred organization. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_project
List the details of a project.
Parameter | Type | Description |
|
| Id of the project. If not provided the API will return a details list of all projects. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: list_projects
List the details of all projects.
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_project
Update a project's name or description.
Parameter | Type | Description |
|
| Project Id to which the file belongs. |
|
| The new name for the project. |
|
| The new description for the project. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: delete_project
Delete a project.
Parameter | Type | Description |
|
| Id of the project to delete. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: create_project_collaborator
Add a collaborator to a project.
Parameter | Type | Description |
|
| Id of the project to add the collaborator to. |
|
| User Id of the collaborator to add. |
|
| Gives the right to deploy and stop live algorithms. |
|
| Gives the right to edit the code. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: read_project_collaborators
List all collaborators on a project.
Parameter | Type | Description |
|
| Id of the project from which to read the collaborators. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_project_collaborator
Update collaborator information in a project.
Parameter | Type | Description |
|
| Id of the project the collaborator is on. |
|
| User Id of the collaborator to update. |
|
| Gives the right to deploy and stop live algorithms. |
|
| Gives the right to edit the code. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: delete_project_collaborator
Remove a collaborator from a project.
Parameter | Type | Description |
|
| Id of the project to remove the collaborator from. |
|
| User Id of the collaborator to remove. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: read_project_nodes
Read the available and selected nodes of a project.
Parameter | Type | Description |
|
| Id of the project to which the nodes refer. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_project_nodes
Update the active state of the given nodes to true.
Parameter | Type | Description |
|
| Project Id to which the nodes refer. |
|
| List of node Ids the project may use. If you omit this property or pass an empty list, the best node will be automatically selected for backtest, research, and live trading. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: create_compile
Asynchronously create a compile job request for a project.
Parameter | Type | Description |
|
| Id of the project to compile. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_compile
Read a compile packet job result.
Parameter | Type | Description |
|
| Id of the project you requested to compile. |
|
| Compile Id returned during the creation request. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: create_file
Add a file to a given project.
Parameter | Type | Description |
|
| Id of the project to add the file. |
|
| The name of the new file. |
|
| The content of the new file. |
|
| Name of the environment that's creating the request. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: read_file
Read a file from a project, or all files in the project if no file name is provided.
Parameter | Type | Description |
|
| Id of the project that contains the file. |
|
| The name of the file to read. |
|
| Name of the environment that's creating the request. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_file_name
Update the name of a file.
Parameter | Type | Description |
|
| Id of the project that contains the file. |
|
| The current name of the file. |
|
| The new name for the file. |
|
| Name of the environment that's creating the request. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: update_file_contents
Update the contents of a file.
Parameter | Type | Description |
|
| Id of the project that contains the file. |
|
| The name of the file to update. |
|
| The new contents of the file. |
|
| Name of the environment that's creating the request. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: delete_file
Delete a file in a project.
Parameter | Type | Description |
|
| Id of the project that contains the file. |
|
| The name of the file to delete. |
|
| Name of the environment that's creating the request. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: create_backtest
Create a new backtest request and get the backtest Id.
Parameter | Type | Description |
|
| Id of the project to backtest. |
|
| Compile Id for the project to backtest. |
|
| Name for the new backtest. |
|
| Parameters to use for the backtest. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_backtest
Read the results of a backtest.
Parameter | Type | Description |
|
| Id of the project that contains the backtest. |
|
| Id of the backtest to read. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: list_backtests
List all the backtests for the project.
Parameter | Type | Description |
|
| Id of the project from which to read one or multiple backtests. |
|
| If true, the backtests summaries from the response will contain the statistics with their corresponding values. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: read_backtest_chart
Read a chart from a backtest.
Parameter | Type | Description |
|
| Id of the project that contains the backtest. |
|
| Id of the backtest for this chart request. |
|
| The requested chart name. |
|
| The number of data points to request. |
|
| The start timestamp of the request in Unix time. |
|
| The end timestamp of the request in Unix time. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: read_backtest_orders
Read out the orders of a backtest.
Parameter | Type | Description |
|
| Starting index of the orders to be fetched. |
|
| Last index of the orders to be fetched. Note that end - start must be less than 100. |
|
| Id of the project from which to read the backtest. |
|
| Id of the backtest from which to read the orders. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: read_backtest_insights
Read out the insights of a backtest.
Parameter | Type | Description |
|
| Starting index of the insights to be fetched. |
|
| Last index of the insights to be fetched. Note that end - start must be less than 100. |
|
| Id of the project from which to read the backtest. |
|
| Id of the backtest from which to read the insights. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_backtest
Update the name or note of a backtest.
Parameter | Type | Description |
|
| Id of the project that contains the backtest. |
|
| Id of the backtest to update. |
|
| Name to assign to the backtest. |
|
| Note to attach to the backtest. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: delete_backtest
Delete a backtest from a project.
Parameter | Type | Description |
|
| Id of the project that contains the backtest. |
|
| Id of the backtest to delete. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: estimate_optimization_time
Estimate the execution time of an optimization with the specified parameters.
Parameter | Type | Description |
|
| Id of the project to optimize. |
|
| Name of the optimization. |
|
| Target statistic of the optimization to minimize or maximize. |
|
| Target extremum of the optimization. |
|
| Desired value for the optimization target statistic. |
|
| Optimization strategy. |
|
| Optimization compile Id. |
|
| Optimization parameters. |
|
| Optimization constraints. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: create_optimization
Create an optimization with the specified parameters.
Parameter | Type | Description |
|
| Id of the project to optimize. |
|
| Name of the optimization. |
|
| Target statistic of the optimization to minimize or maximize. |
|
| Target extremum of the optimization. |
|
| Desired value for the optimization target statistic. |
|
| Optimization strategy. |
|
| Optimization compile Id. |
|
| Optimization parameters. |
|
| Optimization constraints. |
|
| Estimated cost for optimization. |
|
| Optimization node type. |
|
| Number of parallel nodes for optimization. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_optimization
Read an optimization.
Parameter | Type | Description |
|
| Id of the optimization to read. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: list_optimizations
List all the optimizations for a project.
Parameter | Type | Description |
|
| Id of the Project to get a list of optimizations for. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_optimization
Update the name of an optimization.
Parameter | Type | Description |
|
| Id of the optimization to update. |
|
| Name to assign to the optimization. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: abort_optimization
Abort an optimization.
Parameter | Type | Description |
|
| Id of the optimization to abort. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: delete_optimization
Delete an optimization.
Parameter | Type | Description |
|
| Id of the optimization to delete. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: authorize_connection
Authorize an external connection with a live brokerage or data provider.
Parameter | Type | Description |
|
| The brokerage to authenticate a connection with. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: create_live_algorithm
Create a live algorithm.
Parameter | Type | Description |
|
| The version of the Lean used to run the algorithm. -1 is master, however, sometimes this can create problems with live deployments. If you experience problems using, try specifying the version of Lean you would like to use. |
|
| Project Id. |
|
| Compile Id. |
|
| Id of the node that will run the algorithm. |
|
| Brokerage configuration for the live algorithm. |
|
| Dictionary of data provider configurations to be used in the live algorithm. Provide at least one. The order in which you define the providers defines their order of precedence. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_live_algorithm
Read details of a live algorithm.
Parameter | Type | Description |
|
| Id of the project to read. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: list_live_algorithms
List all your past and current live trading deployments.
Parameter | Type | Description |
|
| Status of the live algorithms to include in the response. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_live_chart
Read a chart from a live algorithm.
Parameter | Type | Description |
|
| Id of the project that's live trading. |
|
| Name of the chart to read. |
|
| The number of data points to request. |
|
| The unix start time of the request. |
|
| The unix end time of the request. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_live_logs
Get the logs of a live algorithm.
Parameter | Type | Description |
| `` optional | Format of the log results. |
|
| Id of the project that contains the live running algorithm. |
|
| Deploy Id (Algorithm Id) of the live running algorithm. |
|
| Start line (inclusive) of logs to read. The lines numbers start at 0. |
|
| End line (exclusive) of logs to read, where endLine - startLine <= 250. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_live_portfolio
Read out the portfolio state of a live algorithm.
Parameter | Type | Description |
|
| Id of the project from which to read the live algorithm. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_live_orders
Read out the orders of a live algorithm.
Parameter | Type | Description |
|
| Starting index of the orders to be fetched. Required if end > 1,000. |
|
| Last index of the orders to be fetched. Note that end - start must be less than 1,000. |
|
| Id of the project from which to read the live algorithm. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_live_insights
Read out the insights of a live algorithm.
Parameter | Type | Description |
|
| Starting index of the insights to be fetched. Required if end > 100. |
|
| Last index of the insights to be fetched. Note that end - start must be less than 100. |
|
| Id of the project from which to read the live algorithm. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: stop_live_algorithm
Stop a live algorithm.
Parameter | Type | Description |
|
| Id of the project to stop trading live. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: liquidate_live_algorithm
Liquidate and stop a live algorithm.
Parameter | Type | Description |
|
| Project Id for the live instance to liquidate. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: create_live_command
Send a command to a live trading algorithm.
Parameter | Type | Description |
|
| Project for the live instance we want to run the command against. |
|
| The command to run. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: broadcast_live_command
Broadcast a live command to all live algorithms in an organization.
Parameter | Type | Description |
|
| Organization Id of the projects we would like to broadcast the command to |
|
| Project for the live instance we want to exclude from the broadcast list. If null, all projects will be included. |
|
| The command to run. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: upload_object
Upload files to the Object Store.
Parameter | Type | Description |
|
| Orgainization ID. |
|
| Unique key to access the object in Object Store. |
|
| Object data to be stored. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: read_object_properties
Get Object Store properties of a specific organization and key.
Parameter | Type | Description |
|
| Id of the organization that owns the Object Store. |
|
| Key in the Object Store. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: read_object_store_file_job_id
Create a job to download files from the Object Store and then read the job Id.
Parameter | Type | Description |
|
| Id of the organization that owns the Object Store. |
|
| Keys of the Object Store files. |
This tool modifies it's environment.
This tool doesn't perform destructive updates.
Calling this tool repeatedly with the same arguments has additional effects.
This tool may interact with an "open world" of external entities.
Tool: read_object_store_file_download_url
Get the URL for downloading files from the Object Store.
Parameter | Type | Description |
|
| Id of the organization that owns the Object Store. |
|
| Id of the download job for the files. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: list_object_store_files
List the Object Store files under a specific directory in an organization.
Parameter | Type | Description |
|
| Id of the organization to list the Object Store files from. |
|
| Path to a directory in the Object Store. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: delete_object
Delete the Object Store file of a specific organization and key.
Parameter | Type | Description |
|
| Id of the organization that owns the Object Store. |
|
| Key of the Object Store file to delete. |
This tool modifies it's environment.
This tool may perform destructive updates.
Calling this tool repeatedly with the same arguments has no additional effect.
This tool may interact with an "open world" of external entities.
Tool: read_lean_versions
Returns a list of LEAN versions with basic information for each version.
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: check_initialization_errors
Run a backtest for a few seconds to initialize the algorithm and get inialization errors if any.
Parameter | Type | Description |
|
| Programming language. |
|
| Files to process. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: complete_code
Show the code completion for a specific text input.
Parameter | Type | Description |
|
| Programming language for the code completion. |
|
| Sentence to complete. |
|
| Maximum size of the responses. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: enhance_error_message
Show additional context and suggestions for error messages.
Parameter | Type | Description |
|
| Programming language for the code completion. |
|
| Error message to enhance. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: update_code_to_pep8
Update Python code to follow PEP8 style.
Parameter | Type | Description |
|
| Files of the project. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: check_syntax
Check the syntax of a code.
Parameter | Type | Description |
|
| Programming language. |
|
| Files to process. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Tool: search_quantconnect
Search for content in QuantConnect.
Parameter | Type | Description |
|
| Programming language of the content to search. |
|
| Criteria for the search. |
This tool doesn't modify it's environment.
This tool may interact with an "open world" of external entities.
Debugging
Build
To build the Docker image from source, clone this repository and then run docker build -t quantconnect/mcp-server ..
Logs
To log to the mcp-server-quantconnect.log file, import sys and then print("Hello world", file=sys.stderr).
Inspector
To start the inspector, run npx @modelcontextprotocol/inspector uv run src/main.py.
To pass a model to the inspector tool, use JSON (for example, {"name":"My Project","language":"Py"}).
Force redeploy Thu Aug 14 23:50:18 PDT 2025
Available Tools
63 toolsabort_optimizationCIdempotent
Abort an optimization.
Inputs: model (required). Returns: errors, success
authorize_connectionAIdempotent
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.
Inputs: model (required). Returns: errors, success, authorization
broadcast_live_commandC
Broadcast a live command to all live algorithms in an organization.
Inputs: model (required). Returns: errors, success
check_initialization_errorsBRead-only
Run a backtest for a few seconds to initialize the algorithm and get inialization errors if any.
Inputs: model (required). Returns: state, payload, version, payloadType
check_syntaxCRead-only
Check the syntax of a code.
Inputs: model (required). Returns: state, payload, version, payloadType
complete_codeCRead-only
Show the code completion for a specific text input.
Inputs: model (required). Returns: state, payload, version, payloadType
create_backtestB
Create a new backtest request and get the backtest Id.
Inputs: model (required). Returns: errors, success, backtest, debugging
create_compileB
Asynchronously create a compile job request for a project.
Inputs: model (required). Returns: state, errors, success, compileId, +4 more
create_fileBIdempotent
Add a file to a given project.
Inputs: model (required). Returns: files, errors, success
create_live_algorithmD
Create a live algorithm.
Inputs: model (required). Returns: live, errors, source, success, +4 more
create_live_commandC
Send a command to a live trading algorithm.
Inputs: model (required). Returns: errors, success
create_optimizationC
Create an optimization with the specified parameters.
Inputs: model (required). Returns: errors, success, optimizations
create_projectB
Create a new project in your default organization.
Inputs: model (required). Returns: errors, success, projects, versions
create_project_collaboratorBIdempotent
Add a collaborator to a project.
Inputs: model (required). Returns: success, collaborators
delete_backtestAIdempotent
Delete a backtest from a project.
Inputs: model (required). Returns: errors, success
delete_fileBIdempotent
Delete a file in a project.
Inputs: model (required). Returns: errors, success
delete_objectBIdempotent
Delete the Object Store file of a specific organization and key.
Inputs: model (required). Returns: errors, success
delete_optimizationBIdempotent
Delete an optimization.
Inputs: model (required). Returns: errors, success
delete_projectCIdempotent
Delete a project.
Inputs: model (required). Returns: errors, success
delete_project_collaboratorCIdempotent
Remove a collaborator from a project.
Inputs: model (required). Returns: success, collaborators
enhance_error_messageBRead-only
Show additional context and suggestions for error messages.
Inputs: model (required). Returns: state, payload, version, payloadType
estimate_optimization_timeCRead-only
Estimate the execution time of an optimization with the specified parameters.
Inputs: model (required). Returns: errors, success, estimate
liquidate_live_algorithmCIdempotent
Liquidate and stop a live algorithm.
Inputs: model (required). Returns: errors, success
list_backtestsBRead-only
List all the backtests for the project.
Inputs: model (required). Returns: count, errors, success, backtests
list_live_algorithmsB
List all your past and current live trading deployments.
Inputs: model (required). Returns: live, errors, success
list_object_store_filesBRead-only
List the Object Store files under a specific directory in an organization.
Inputs: model (required). Returns: page, path, errors, objects, +4 more
list_optimizationsARead-only
List all the optimizations for a project.
Inputs: model (required). Returns: errors, success, optimizations
list_projectsARead-only
List the details of all projects.
Inputs: no named parameters. Returns: errors, success, projects, versions
lock_project_with_collaboratorsBIdempotent
Lock a project that has collaborators so you can edit it.
Inputs: model (required). Returns: errors, success
read_accountARead-only
Read the organization account status.
Inputs: no named parameters. Returns: card, creditBalance, organizationId
read_backtestBRead-only
Read the results of a backtest.
Inputs: model (required). Returns: errors, success, backtest, debugging
read_backtest_chartCRead-only
Read a chart from a backtest.
Inputs: model (required). Returns: chart, errors, success
read_backtest_insightsCRead-only
Read out the insights of a backtest.
Inputs: model (required). Returns: length, success, insights
read_backtest_ordersCRead-only
Read out the orders of a backtest.
Inputs: model (required). Returns: length, orders
read_compileBRead-only
Read a compile packet job result.
Inputs: model (required). Returns: logs, state, errors, success, +1 more
read_fileARead-only
Read a file from a project, or all files in the project if no file name is provided.
Inputs: model (required). Returns: files, errors, success
read_latest_mcp_server_versionBRead-only
Returns the latest version of the QC MCP Server released.
Inputs: no named parameters. Returns: result
read_lean_versionsARead-only
Returns a list of LEAN versions with basic information for each version.
Inputs: no named parameters. Returns: errors, success, versions
read_live_algorithmC
Read details of a live algorithm.
Inputs: model (required). Returns: files, charts, errors, public, +13 more
read_live_chartC
Read a chart from a live algorithm.
Inputs: model (required). Returns: result
read_live_insightsB
Read out the insights of a live algorithm.
The snapshot updates about every 10 minutes.
Inputs: model (required). Returns: length, success, insights
read_live_logsA
Get the logs of a live algorithm.
The snapshot updates about every 5 minutes.
Inputs: model (required). Returns: logs, errors, length, success, +1 more
read_live_ordersC
Read out the orders of a live algorithm.
The snapshot updates about every 10 minutes.
Inputs: model (required). Returns: result
read_live_portfolioB
Read out the portfolio state of a live algorithm.
The snapshot updates about every 10 minutes.
Inputs: model (required). Returns: errors, success, portfolio
read_mcp_server_versionARead-only
Returns the version of the QC MCP Server that's running.
Inputs: no named parameters. Returns: result
read_object_propertiesARead-only
Get Object Store properties of a specific organization and key.
It doesn't work if the key is a directory in the Object Store.
Inputs: model (required). Returns: errors, success, metadata
read_object_store_file_download_urlBRead-only
Get the URL for downloading files from the Object Store.
Inputs: model (required). Returns: url, jobId, errors, success
read_object_store_file_job_idC
Create a job to download files from the Object Store and then read the job Id.
Inputs: model (required). Returns: url, jobId, errors, success
read_optimizationCRead-only
Read an optimization.
Inputs: model (required). Returns: errors, success, optimization
read_projectBRead-only
List the details of a project.
Inputs: model (required). Returns: errors, success, projects, versions
read_project_collaboratorsARead-only
List all collaborators on a project.
Inputs: model (required). Returns: success, collaborators, userLiveControl, userPermissions
read_project_nodesARead-only
Read the available and selected nodes of a project.
Inputs: model (required). Returns: nodes, errors, success, autoSelectNode
search_quantconnectBRead-only
Search for content in QuantConnect.
Inputs: model (required). Returns: state, version, messageId, retrivals
stop_live_algorithmBIdempotent
Stop a live algorithm.
Inputs: model (required). Returns: errors, success
update_backtestAIdempotent
Update the name or note of a backtest.
Inputs: model (required). Returns: errors, success
update_code_to_pep8CRead-only
Update Python code to follow PEP8 style.
Inputs: model (required). Returns: state, payload, version, payloadType
update_file_contentsCIdempotent
Update the contents of a file.
Inputs: model (required). Returns: files, errors, success
update_file_nameBIdempotent
Update the name of a file.
Inputs: model (required). Returns: errors, success
update_optimizationBIdempotent
Update the name of an optimization.
Inputs: model (required). Returns: errors, success
update_projectAIdempotent
Update a project's name or description.
Inputs: model (required). Returns: errors, success
update_project_collaboratorBIdempotent
Update collaborator information in a project.
Inputs: model (required). Returns: success, collaborators
update_project_nodesCIdempotent
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.
Inputs: model (required). Returns: nodes, errors, success, autoSelectNode
upload_objectCIdempotent
Upload files to the Object Store.
Inputs: model (required). Returns: errors, success
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 63 tools
Most tools have distinct purposes with clear resource-action pairs (e.g., create_backtest vs. read_backtest vs. delete_backtest). However, some overlap exists in object store operations (read_object_properties, read_object_store_file_download_url, read_object_store_file_job_id) and live algorithm monitoring tools (read_live_insights, read_live_orders, read_live_portfolio) that could cause minor confusion about which to use for specific queries.
Tool names follow a highly consistent verb_noun pattern throughout (e.g., create_backtest, list_backtests, read_backtest, delete_backtest). All tools use snake_case with clear action verbs (create, read, update, delete, list, etc.) and specific nouns, making them predictable and easy to parse.
With 63 tools, the count is excessive for typical MCP server purposes, making it overwhelming for agents to navigate. While the domain (QuantConnect platform) is broad, many tools could be consolidated (e.g., multiple object store read operations) or omitted to reduce cognitive load and improve usability.
The tool set provides comprehensive coverage for the QuantConnect domain, including full CRUD operations for projects, backtests, optimizations, files, and live algorithms. It also includes specialized tools for syntax checking, code completion, error enhancement, and platform-specific features like object store management and node selection, leaving no obvious gaps for core workflows.
Related MCP Connectors
Build, backtest, and deploy quantitative trading strategies from your AI agent.
Connect brokerage accounts to AI assistants: holdings, orders, asset lookup, and approved trading.
Unified financial infrastructure connecting AI agents directly to trade live/demo brokerage accounts, Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, and prediction markets, institutional research feeds, and algorithmic strategy backtesters.
AI agents backtest, paper trade and live trade via your broker. Free to connect; OAuth.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with QuantConnect's algorithmic trading platform to create projects, write trading strategies, run backtests, perform optimizations, and deploy algorithms to live trading through the QuantConnect API.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables natural language trading operations through AI assistants using Alpaca's Trading API. Supports stocks, options, crypto trading, portfolio management, and real-time market data access.MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants like Claude to run backtests, fetch market data, list strategies, and analyze trading algorithms via natural language.1,141GPL 3.0

panther-mcpofficial
AlicenseAqualityDmaintenanceEnables AI assistants to backtest trading strategies described in plain English, providing access to market data, technical indicators, and comprehensive performance reports.131MIT