ot_rest · Ttt MCP: Risk & Policy

WHAT IT DOES

What ot_rest does on Ttt

AI agents invoke ot_rest to trigger actions in Ttt. 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 ot_rest needs a policy

Although the server advertises tic-tac-toe tools, this tool (ot_rest) appears to belong to a different game context (likely a survival/adventure game based on resource management and health recovery mechanics). The tool triggers an operation with state-changing consequences (time passage, resource depletion, health restoration) that are conditional on game parameters.

From the tool's definition Tool performs an action with ongoing effects ('make camp and rest for 1–3 days') that consumes resources ('costs food and time') and modifies game state ('recovers health for everyone'). This is a deliberate game mechanic invocation, not a query.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ot_rest Rate-limited

ot_rest 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": {
    "ot_rest": {
      "limits": [
        {
          "counter": "ot_rest_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 Ttt, so you can run agents against it safely.

FAQ

Questions about ot_rest

What does the ot_rest tool do? +

Make camp and rest for 1–3 days. Recovers health for everyone but costs food and time. Worth it when someone is struggling. It is categorised as a Execute tool in the Ttt MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ot_rest? +

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

What risk level is ot_rest? +

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

Can I rate-limit ot_rest? +

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

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

ot_rest is provided by the Ttt MCP server (srmtech-git/mcparcade). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.