ms_new_game · Ttt MCP: Risk & Policy

WHAT IT DOES

What ms_new_game does on Ttt

AI agents invoke ms_new_game 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 ms_new_game needs a policy

This tool starts a game simulation with state initialization. While it is not destructive (no data deleted), not financial, and not a simple read (it performs computational work and modifies game state), it represents code execution that triggers a game engine. The blast radius is low since the operation is scoped to a game session with no external side effects or persistent data damage.

From the tool's definition Tool initializes a game state with procedural mine placement ('9×9 field, 10 hidden mines') and triggers game logic ('The first step is always safe — mines are placed after it').

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ms_new_game Rate-limited

ms_new_game 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": {
    "ms_new_game": {
      "limits": [
        {
          "counter": "ms_new_game_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 ms_new_game

What does the ms_new_game tool do? +

Start a new Fluffling minefield crossing. 9×9 field, 10 hidden mines. The first step is always safe — mines are placed after it. Call ms_reveal_cell to send the first scout. 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 ms_new_game? +

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

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

Can I rate-limit ms_new_game? +

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

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

ms_new_game 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.