run_cron · Habitca MCP: Risk & Policy

WHAT IT DOES

What run_cron does on Habitca

AI agents invoke run_cron to trigger actions in Habitca. 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_cron needs a policy

This tool executes a scheduled operation with side effects that cannot be easily reversed. While not technically destructive (the changes persist but cron can run again), it triggers complex game logic that affects user state (health damage, day advancement). An AI agent calling this at the wrong time could cause unintended game state consequences.

From the tool's definition Tool description states it 'Run[s] the daily cron (advance day, apply damage from missed dailies)' — an autonomous operation that triggers state changes in the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_cron Rate-limited

run_cron 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_cron": {
      "limits": [
        {
          "counter": "run_cron_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 Habitca, so you can run agents against it safely.

FAQ

Questions about run_cron

What does the run_cron tool do? +

Run the daily cron (advance day, apply damage from missed dailies). Normally auto-runs on first action of the day. It is categorised as a Execute tool in the Habitca 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_cron? +

Register the Habitca MCP server in PolicyLayer and add a rule for run_cron: 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 Habitca. Nothing to install.

What risk level is run_cron? +

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

Can I rate-limit run_cron? +

Yes. Add a rate_limit block to the run_cron 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_cron completely? +

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

run_cron is provided by the Habitca MCP server (leon-jarvis1/habitca_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.