solve_level · Ice Puzzle MCP: Risk & Policy

WHAT IT DOES

What solve_level does on Ice Puzzle

AI agents invoke solve_level to trigger actions in Ice Puzzle. 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 solve_level needs a policy

This tool executes code (a breadth-first search algorithm) to analyze and return solver diagnostics about the current level. While not destructive or modifying persisted state directly, it triggers an external computational operation whose behavior depends on the level configuration. The side effects (generating solver feedback, diagnostics) are transient and reversible, placing it in Execute rather than Write.

From the tool's definition Tool performs an algorithmic operation ('Run BFS solver') on a game level state, executing a computational process with observable effects on solver analysis.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

solve_level Rate-limited

solve_level 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": {
    "solve_level": {
      "limits": [
        {
          "counter": "solve_level_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 Ice Puzzle, so you can run agents against it safely.

FAQ

Questions about solve_level

What does the solve_level tool do? +

Run BFS solver on current level with direction balance and unsolvable diagnostics. It is categorised as a Execute tool in the Ice Puzzle MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on solve_level? +

Register the Ice Puzzle MCP server in PolicyLayer and add a rule for solve_level: 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 Ice Puzzle. Nothing to install.

What risk level is solve_level? +

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

Can I rate-limit solve_level? +

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

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

solve_level is provided by the Ice Puzzle MCP server (wmoten/ice-puzzle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.