Walk-Forward Backtest as a Service: Run a candle-replay backtest with walk-forward cross-validation against any of Einstein's 4 production-grade strategy adapters (sma-crossover, rsi-mean-reversion, momentum-breakout, buy-and-hold). Returns Sortino, max-drawdown, total return, profit-factor and p...
Part of the Agent Einstein — Autonomous Crypto Intelligence server.
Free to start. No card required.
AI agents invoke backtest_strategy to trigger processes or run actions in Agent Einstein — Autonomous Crypto Intelligence. 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.
backtest_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": {
"backtest_strategy": {
"limits": [
{
"counter": "backtest_strategy_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Agent Einstein — Autonomous Crypto Intelligence policy for all 72 tools.
These attack patterns abuse exactly the kind of access backtest_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.
Walk-Forward Backtest as a Service: Run a candle-replay backtest with walk-forward cross-validation against any of Einstein's 4 production-grade strategy adapters (sma-crossover, rsi-mean-reversion, momentum-breakout, buy-and-hold). Returns Sortino, max-drawdown, total return, profit-factor and per-fold breakdown so the caller can vet a strategy on real out-of-sample data before risking capital. Caller specifies adapter id + symbol + timeframe + fold config; results come back in seconds.. It is categorised as a Execute tool in the Agent Einstein — Autonomous Crypto Intelligence MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agent Einstein — Autonomous Crypto Intelligence MCP server in PolicyLayer and add a rule for backtest_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 Agent Einstein — Autonomous Crypto Intelligence. Nothing to install.
backtest_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 backtest_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 backtest_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.
backtest_strategy is provided by the Agent Einstein — Autonomous Crypto Intelligence MCP server (https://emc2ai.io/api/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 72 Agent Einstein — Autonomous Crypto Intelligence 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.