Run StratProof's honest backtest on a trading strategy. Tests the strategy description against 3 years of real Binance data with real fees and slippage, returns a CONFIRMED / MIXED / DEBUNKED verdict plus detailed statistics. This is the same engine that powers the public /prove page — no simplif...
Part of the StratProof server.
Free to start. No card required.
AI agents invoke prove_strategy to trigger processes or run actions in StratProof. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
prove_strategy can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"prove_strategy": {
"limits": [
{
"counter": "prove_strategy_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full StratProof policy for all 6 tools.
These attack patterns abuse exactly the kind of access prove_strategy gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run StratProof's honest backtest on a trading strategy. Tests the strategy description against 3 years of real Binance data with real fees and slippage, returns a CONFIRMED / MIXED / DEBUNKED verdict plus detailed statistics. This is the same engine that powers the public /prove page — no simplification, no shortcuts. Use this whenever a user describes a trading strategy and wants to know whether it would actually make money with real fees.. It is categorised as a Execute tool in the StratProof MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the StratProof MCP server in PolicyLayer and add a rule for prove_strategy: 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 StratProof. Nothing to install.
prove_strategy 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 prove_strategy 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 prove_strategy. 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.
prove_strategy is provided by the StratProof MCP server (pmort2222/stratproof). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 StratProof tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.