backtest_strategy

THE RISK

High Risk

Why backtest_strategy needs a policy

Backtesting executes a trading strategy simulation engine against datasets, which constitutes running code/computation with potentially significant consequences if misused (e.g., generating misleading results that inform real trades). While it doesn't directly move money, it falls under Execute due to running strategy logic/computation.

From the tool's definition 'Backtest a trading strategy on historical data' — runs a strategy simulation/execution engine against historical data using presets, triggering complex computational operations whose results depend on the provided arguments

Documented attack patterns abuse exactly the kind of access backtest_strategy gives an agent:

POLICY

How to control backtest_strategy

PolicyLayer is an MCP gateway — it sits between your AI agents and Momentum, and nothing reaches the server without passing your rules. This is the rule we recommend for backtest_strategy:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "backtest_strategy": {
      "limits": [
        {
          "counter": "backtest_strategy_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

backtest_strategy 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.

Create a free account and register Momentum — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Momentum tools

Financial find_best_to_sell Auto-find the best puts and calls to SELL. Scans 7-45 DTE across Execute run_custom_screen run_custom_screen Execute run_stock_screen run_stock_screen Execute sweep_strategy Run a strategy across multiple tickers (max 20). Ranks by Sharpe/return. Execute walk_forward_test Walk-forward validation: splits data into n folds, detects overfitting. Write log_conviction Log a trade conviction to the journal. Direction: long/short. Write save_strategy Save a custom strategy to disk for re-use. Read analyze_breadth Get a comprehensive market breadth health score (0-100).

All 52 Momentum tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Momentum → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about backtest_strategy

What does the backtest_strategy tool do? +

Backtest a trading strategy on historical data. 6 presets:. It is categorised as a Execute tool in the Momentum MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on backtest_strategy? +

Register the Momentum 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 Momentum. Nothing to install.

What risk level is backtest_strategy? +

backtest_strategy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit backtest_strategy? +

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.

How do I block backtest_strategy completely? +

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.

What MCP server provides backtest_strategy? +

backtest_strategy is provided by the Momentum MCP server (mphinance/momentum-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Momentum tool call.

Start from Momentum, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →