AI agents invoke run_backtest to trigger actions in MaverickMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes financial backtesting logic, which runs code/algorithms whose effects depend on supplied arguments (historical data ranges, strategy parameters, portfolio composition). While not immediately destructive or financial in the sense of moving real money, execution of arbitrary backtests could generate misleading signals for investment decisions if misused.
From the tool's definition Tool name 'run_backtest' combined with sibling tools including 'backtest_portfolio', 'create_strategy_ensemble', and 'compare_strategies' indicates execution of financial backtesting algorithms.
Documented attack patterns abuse exactly the kind of access run_backtest gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MaverickMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_backtest:
{
"version": "1",
"default": "deny",
"tools": {
"run_backtest": {
"limits": [
{
"counter": "run_backtest_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_backtest stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
run_backtest. It is categorised as a Execute tool in the MaverickMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Maverick MCP server in PolicyLayer and add a rule for run_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 MaverickMCP. Nothing to install.
run_backtest is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_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 run_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.
run_backtest is provided by the Maverick MCP server (wshobson/maverick-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 54 MaverickMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
54 MaverickMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.