Read backtest results and statistics from a project. Args: project_id: ID of the project containing the backtest backtest_id: ID of the specific backtest to read chart: Optional chart name to include chart data in response Returns: Dictionary containing backtest results, statistics, and optional ...
AI agents call read_backtest to retrieve information from QuantConnect MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries existing backtest data without side effects. It fits the Read category definition: 'retrieves or queries data; no side effects (search, list, get, fetch).' Even though the server is a trading platform, this specific tool does not execute trades, modify strategies, or trigger financial transactions—it merely reads historical backtest results.
From the tool's definition Tool name is 'read_backtest' and description states it 'Read backtest results and statistics from a project' with no mention of modification, deletion, or execution of trades.
Documented attack patterns abuse exactly the kind of access read_backtest gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and QuantConnect MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for read_backtest:
{
"version": "1",
"default": "deny",
"tools": {
"read_backtest": {}
}
}read_backtest is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read backtest results and statistics from a project. Args: project_id: ID of the project containing the backtest backtest_id: ID of the specific backtest to read chart: Optional chart name to include chart data in response Returns: Dictionary containing backtest results, statistics, and optional chart data. It is categorised as a Read tool in the QuantConnect MCP Server MCP Server, which means it retrieves data without modifying state.
Register the QuantConnect MCP Server MCP server in PolicyLayer and add a rule for read_backtest: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches QuantConnect MCP Server. Nothing to install.
read_backtest is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_backtest rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for read_backtest. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
read_backtest is provided by the QuantConnect MCP Server MCP server (taylorwilsdon/quantconnect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 50 QuantConnect MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
50 QuantConnect MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.