backtest · Forecast MCP: Risk & Policy

WHAT IT DOES

What backtest does on Forecast

AI agents invoke backtest to trigger actions in Forecast. 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 needs a policy

Backtesting in a forecasting context typically involves running a model against historical data to evaluate performance — this is an execution/computation operation with no direct data modification. However, the description is empty, so confidence is low. Given the server context (time-series forecasting), it most likely runs computations rather than reading static data or writing/deleting anything.

From the tool's definition Tool name 'backtest' on a forecasting server; description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

backtest Rate-limited

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": {
    "backtest": {
      "limits": [
        {
          "counter": "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 Forecast, so you can run agents against it safely.

FAQ

Questions about backtest

What does the backtest tool do? +

backtest. It is categorised as a Execute tool in the Forecast 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? +

Register the Forecast MCP server in PolicyLayer and add a rule for 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 Forecast. Nothing to install.

What risk level is backtest? +

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

Can I rate-limit backtest? +

Yes. Add a rate_limit block to the 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 backtest completely? +

Set action: deny in the PolicyLayer policy for 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 backtest? +

backtest is provided by the Forecast MCP server (ramdhavepreetam/timesfm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.