cc_catch · Ttt MCP: Risk & Policy

WHAT IT DOES

What cc_catch does on Ttt

AI agents invoke cc_catch 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 cc_catch needs a policy

This is an Execute tool because it runs an operation (creature capture attempt) whose outcome is non-deterministic and depends on game state. It is not Read (no side effects), not Write (capture is not a simple reversible creation), not Destructive (game can be reset), and not Financial. Severity is high because an AI agent could spam captures, exhaust resources, or trigger unintended game state transitions.

From the tool's definition Tool description states 'Attempt to catch the creature currently encountered' — this triggers a game action that changes state based on timing and probability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cc_catch Rate-limited

cc_catch 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": {
    "cc_catch": {
      "limits": [
        {
          "counter": "cc_catch_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 cc_catch

What does the cc_catch tool do? +

Attempt to catch the creature currently encountered. Only usable when a creature has appeared. 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 cc_catch? +

Register the Ttt MCP server in PolicyLayer and add a rule for cc_catch: 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 cc_catch? +

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

Can I rate-limit cc_catch? +

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

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

cc_catch 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.