backtest_pine_grid · PineForge-Codegen MCP: Risk & Policy

WHAT IT DOES

What backtest_pine_grid does on PineForge-Codegen

AI agents invoke backtest_pine_grid to trigger actions in PineForge-Codegen. 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 backtest_pine_grid needs a policy

This tool executes code (transpiled PineScript → C++) inside Docker containers across a parameter grid. It triggers external compute operations (Docker runs) whose effects and resource consumption depend on the arguments supplied. No money is moved and data is not irreversibly deleted, but arbitrary code execution in containers with potentially large grid sweeps poses significant blast-radius risk if misused.

From the tool's definition 'optimize, sweep, tune, or compare PineScript parameter values' — runs multiple backtests via Docker by transpiling Pine to C++ and executing it on the PineForge engine

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

backtest_pine_grid Rate-limited

backtest_pine_grid 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": {
    "backtest_pine_grid": {
      "limits": [
        {
          "counter": "backtest_pine_grid_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 PineForge-Codegen, so you can run agents against it safely.

FAQ

Questions about backtest_pine_grid

What does the backtest_pine_grid tool do? +

Use when the user wants to optimize, sweep, tune, or compare PineScript parameter values. It is categorised as a Execute tool in the PineForge-Codegen 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_pine_grid? +

Register the PineForge-Codegen MCP server in PolicyLayer and add a rule for backtest_pine_grid: 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 PineForge-Codegen. Nothing to install.

What risk level is backtest_pine_grid? +

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

Can I rate-limit backtest_pine_grid? +

Yes. Add a rate_limit block to the backtest_pine_grid 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_pine_grid completely? +

Set action: deny in the PolicyLayer policy for backtest_pine_grid. 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_pine_grid? +

backtest_pine_grid is provided by the PineForge-Codegen MCP server (oci:ghcr.io/pineforge-4pass/pineforge-codegen-mcp:v0.9.2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.