AI agents call delete_backtest to permanently remove resources in QuantConnect — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of backtests is an irreversible operation that removes data permanently. In a financial research context (QuantConnect is an algorithmic trading platform), backtests represent historical analysis and validation work that cannot be recovered once deleted. This warrants the Destructive category and high severity due to potential loss of important research records and analysis artifacts.
From the tool's definition Tool name is 'delete_backtest' and description states 'Delete a backtest from a project.' The verb 'delete' combined with the irreversible nature of removing a backtest record clearly indicates a destructive operation.
Documented attack patterns abuse exactly the kind of access delete_backtest gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and QuantConnect, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_backtest:
{
"version": "1",
"default": "deny",
"hide": [
"delete_backtest"
]
}delete_backtest disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a backtest from a project. It is categorised as a Destructive tool in the QuantConnect MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the QuantConnect MCP server in PolicyLayer and add a rule for delete_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. Nothing to install.
delete_backtest is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_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 delete_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.
delete_backtest is provided by the QuantConnect MCP server (quantconnect/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 64 QuantConnect tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
64 QuantConnect tools catalogued and risk-classified — across an index of 42,500+ MCP servers.