roll_dice · MCP Server App MCP: Risk & Policy

WHAT IT DOES

What roll_dice does on MCP Server App

AI agents invoke roll_dice to trigger actions in MCP Server App. 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 roll_dice needs a policy

The tool performs a computation/execution based on provided notation arguments. While the blast radius is minimal (no data written, no external services modified), it is an execution of logic rather than a pure data retrieval. Severity is low as misuse has negligible real-world impact.

From the tool's definition 'Roll the dice with the given notation' — executes a dice-rolling operation based on input notation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

roll_dice Rate-limited

roll_dice 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": {
    "roll_dice": {
      "limits": [
        {
          "counter": "roll_dice_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 MCP Server App, so you can run agents against it safely.

FAQ

Questions about roll_dice

What does the roll_dice tool do? +

Roll the dice with the given notation. It is categorised as a Execute tool in the MCP Server App MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on roll_dice? +

Register the MCP Server App MCP server in PolicyLayer and add a rule for roll_dice: 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 MCP Server App. Nothing to install.

What risk level is roll_dice? +

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

Can I rate-limit roll_dice? +

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

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

roll_dice is provided by the MCP Server App MCP server (ovokpus/mcp-server-app). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.