Run backtest using ML-enhanced strategies. Args: symbol: Stock symbol to backtest strategy_type: ML strategy type (ml_predictor, adaptive, ensemble, regime_aware) start_date: Start date (YYYY-MM-DD) end_date: End date (YYYY-MM-DD) initial_capital: Initial capital amount train_ratio: Ratio of data...
AI agents invoke run_ml_strategy_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 computational operations (ML strategy backtesting) with externally controllable parameters. While it does not move money or delete data (which would be Financial or Destructive), it triggers external algorithmic execution whose results depend on inputs.
From the tool's definition Tool runs backtests using ML-enhanced strategies with configurable parameters (symbol, strategy_type, date range, capital amount, train_ratio).
Documented attack patterns abuse exactly the kind of access run_ml_strategy_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_ml_strategy_backtest:
{
"version": "1",
"default": "deny",
"tools": {
"run_ml_strategy_backtest": {
"limits": [
{
"counter": "run_ml_strategy_backtest_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_ml_strategy_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 using ML-enhanced strategies. Args: symbol: Stock symbol to backtest strategy_type: ML strategy type (ml_predictor, adaptive, ensemble, regime_aware) start_date: Start date (YYYY-MM-DD) end_date: End date (YYYY-MM-DD) initial_capital: Initial capital amount train_ratio: Ratio of data for training (0.0-1.0) Strategy-specific parameters passed as individual arguments Returns: Backtest results with ML-specific metrics. 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_ml_strategy_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_ml_strategy_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_ml_strategy_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_ml_strategy_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_ml_strategy_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.