run_backtest · Nubra MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_backtest does on Nubra MCP Server

AI agents invoke run_backtest to trigger actions in Nubra MCP Server. 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.

WHY IT NEEDS A POLICY

Why run_backtest needs a policy

This tool executes code/algorithms (backtesting engine) rather than simply retrieving static data. Although it operates on historical data and produces no financial transactions or data modifications, the execution of strategy logic with variable outcomes based on parameters classifies it as Execute rather than Read.

From the tool's definition Tool description states 'Run a backtest' with configurable strategy parameters. Backtesting executes trading strategies against historical data with outcomes dependent on input parameters (symbol, timeframe, strategy_type, strategy_params).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_backtest Rate-limited

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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Nubra MCP Server, so you can run agents against it safely.

FAQ

Questions about run_backtest

What does the run_backtest tool do? +

Run a backtest. Required inputs: symbol, timeframe, strategy_type. Supported strategy_type values are ma_crossover and rsi. Optional strategy_params examples: {'fast_window': 20, 'slow_window': 50} or {'rsi_window': 14, 'oversold': 30, 'overbought': 70}. It is categorised as a Execute tool in the Nubra MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_backtest? +

Register the Nubra MCP Server 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 Nubra MCP Server. Nothing to install.

What risk level is run_backtest? +

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

Can I rate-limit run_backtest? +

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.

How do I block run_backtest completely? +

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.

What MCP server provides run_backtest? +

run_backtest is provided by the Nubra MCP Server MCP server (socials-zanskar/nubra-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.