// SCAN REPORT

QuantConnect MCP Server

63 tools. 27 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated: 4 Jul 2026

27 can modify or destroy data

36 read-only

63 tools total

Community server · catalogue entry verified 04/07/2026

How to control QuantConnect MCP Server ↓

TOOL MAP

What QuantConnect MCP Server exposes to your agents

Read (36) Write / Execute (21) Destructive / Financial (6)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous QuantConnect MCP Server tools

Destructive · High delete_backtest This tool permanently removes backtest results and associated data from a QuantConnect project. Destructive · High delete_file This tool permanently removes files from a QuantConnect project without the ability to undo the action. Destructive · High delete_object The tool performs permanent deletion of files from an organization's Object Store. Destructive · High delete_optimization This tool permanently removes an optimization object from the QuantConnect platform.

27 of QuantConnect MCP Server's 63 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control QuantConnect MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and QuantConnect MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_backtest": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_compile": {
    "limits": [
      {
        "counter": "create_compile_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "abort_optimization": {
    "limits": [
      {
        "counter": "abort_optimization_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register QuantConnect MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON QUANTCONNECT →

Instant setup, no code required.

FULL CATALOGUE

All 63 QuantConnect MCP Server tools

DESTRUCTIVE 6 tools

Destructive delete_backtest Delete a backtest from a project. Destructive delete_file Delete a file in a project. Destructive delete_object Delete the Object Store file of a specific organization and Destructive delete_optimization Delete an optimization. Destructive delete_project Delete a project. Destructive delete_project_collaborator Remove a collaborator from a project.

EXECUTE 6 tools

Execute broadcast_live_command Broadcast a live command to all live algorithms in an Execute check_initialization_errors Run a backtest for a few seconds to initialize the algorithm Execute create_backtest Create a new backtest request and get the backtest Id. Execute create_live_command Send a command to a live trading algorithm. Execute create_optimization Create an optimization with the specified parameters. Execute stop_live_algorithm Stop a live algorithm.

WRITE 15 tools

Write create_compile Asynchronously create a compile job request for a project. Write create_file Add a file to a given project. Write create_live_algorithm Create a live algorithm. Write create_project Create a new project in your default organization. Write create_project_collaborator Add a collaborator to a project. Write lock_project_with_collaborators Lock a project so you can edit it. Write update_backtest Update the name or note of a backtest. Write update_code_to_pep8 Update Python code to follow PEP8 style. Write update_file_contents Update the contents of a file. Write update_file_name Update the name of a file. Write update_optimization Update the name of an optimization. Write update_project Update a project's name or description. Write update_project_collaborator Update collaborator information in a project. Write update_project_nodes Update the active state of the given nodes to true. Write upload_object Upload files to the Object Store.

READ 36 tools

Read abort_optimization Abort an optimization. Read authorize_connection authorize_connection Read check_syntax Check the syntax of a code. Read complete_code Show the code completion for a specific text input. Read enhance_error_message Show additional context and suggestions for error messages. Read estimate_optimization_time Estimate the execution time of an optimization with the Read liquidate_live_algorithm Liquidate and stop a live algorithm. Read list_backtests List all the backtests for the project. Read list_live_algorithms List all your past and current live trading deployments. Read list_object_store_files List the Object Store files under a specific directory in Read list_optimizations List all the optimizations for a project. Read list_projects List the details of all projects. Read read_account Read the organization account status. Read read_backtest Read the results of a backtest. Read read_backtest_chart Read a chart from a backtest. Read read_backtest_insights Read out the insights of a backtest. Read read_backtest_orders Read out the orders of a backtest. Read read_compile Read a compile packet job result. Read read_file Read a file from a project, or all files in the project if Read read_latest_mcp_server_version Returns the latest version of the QC MCP Server released. Read read_lean_versions Returns a list of LEAN versions with basic information for Read read_live_algorithm Read details of a live algorithm. Read read_live_chart Read a chart from a live algorithm. Read read_live_insights Read out the insights of a live algorithm. Read read_live_logs Get the logs of a live algorithm. Read read_live_orders Read out the orders of a live algorithm. Read read_live_portfolio Read out the portfolio state of a live algorithm. Read read_mcp_server_version Returns the version of the QC MCP Server that's running. Read read_object_properties Get Object Store properties of a specific organization and Read read_object_store_file_download_url Get the URL for downloading files from the Object Store. Read read_object_store_file_job_id Create a job to download files from the Object Store and Read read_optimization Read an optimization. Read read_project List the details of a project. Read read_project_collaborators List all collaborators on a project. Read read_project_nodes Read the available and selected nodes of a project. Read search_quantconnect Search for content in QuantConnect.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about QuantConnect MCP Server

Can an AI agent delete data through the QuantConnect MCP Server MCP server? +

Yes. The QuantConnect MCP Server server exposes 6 destructive tools including delete_backtest, delete_file, delete_object. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through QuantConnect MCP Server? +

The QuantConnect MCP Server server has 15 write tools including create_compile, create_file, create_live_algorithm. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach QuantConnect MCP Server.

How many tools does the QuantConnect MCP Server MCP server expose? +

63 tools across 4 categories: Destructive, Execute, Read, Write. 36 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on QuantConnect MCP Server? +

Register the QuantConnect MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every QuantConnect MCP Server tool call.

Deterministic rules across all 63 QuantConnect MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON QUANTCONNECT →

Instant setup, no code required.

63 QuantConnect MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.