AI agents call read_backtest to retrieve information from QuantConnect without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries backtest results without creating, modifying, deleting, or executing anything. It is a passive data retrieval operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name is 'read_backtest' and description states 'Read the results of a backtest' — explicitly a read operation with no modification or side effects.
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, 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 the results of a backtest. It is categorised as a Read tool in the QuantConnect MCP Server, which means it retrieves data without modifying state.
Register the QuantConnect 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. 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 (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.