forecast · Forecast MCP: Risk & Policy

WHAT IT DOES

What forecast does on Forecast

AI agents invoke forecast 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 forecast needs a policy

Given the server's purpose, this tool likely runs a forecasting model (either a machine learning model like TimesFM or a statistical computation) against provided time-series data. This constitutes executing an external computation/model inference. It does not appear to read stored data, write/persist results, or have destructive/financial effects, but does trigger external model execution.

From the tool's definition Tool name is 'forecast' on a server described as enabling AI agents to 'forecast time-series data using Google's TimesFM or a zero-dependency statistical baseline.' The tool description itself is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

forecast Rate-limited

forecast 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": {
    "forecast": {
      "limits": [
        {
          "counter": "forecast_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 forecast

What does the forecast tool do? +

forecast. 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 forecast? +

Register the Forecast MCP server in PolicyLayer and add a rule for forecast: 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 forecast? +

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

Can I rate-limit forecast? +

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

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

forecast 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.