AI agents call read_backtest_chart 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.
The tool retrieves backtest chart information, which is a read-only operation that queries existing data. No data creation, modification, deletion, code execution, or financial transactions are implied. The naming convention and context (on a trading platform) confirm it retrieves visualization data for analysis rather than executing trading operations or modifying state.
From the tool's definition Tool name 'read_backtest_chart' indicates reading/retrieving backtest chart data with no modification capability. Description is empty, but the 'read_' prefix and chart retrieval purpose suggest data querying without side effects.
Documented attack patterns abuse exactly the kind of access read_backtest_chart 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_chart:
{
"version": "1",
"default": "deny",
"tools": {
"read_backtest_chart": {}
}
}read_backtest_chart 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_chart. 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_chart: 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_chart 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_chart 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_chart. 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_chart 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.