Roll a dice pool and count successes.
AI agents call roll_pool to retrieve information from Dice MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool executes a deterministic computation on parameters (dice pool configuration) and returns results. While it involves computation, it does not create/modify data (Write), execute arbitrary code or external operations (Execute), delete data (Destructive), or commit financial obligations (Financial). The primary function is retrieving/computing a simulated dice roll outcome.
From the tool's definition roll_pool performs dice rolling with success-counting for TRPG mechanics. The description indicates it 'rolls a dice pool and counts successes' — a computational operation that generates random numbers and performs counting logic without side effects on…
Attacks that exploit this kind of access
Roll a dice pool and count successes. It is categorised as a Read tool in the Dice MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dice MCP Server MCP server in PolicyLayer and add a rule for roll_pool: 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 Dice MCP Server. Nothing to install.
roll_pool is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the roll_pool 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.
Set action: deny in the PolicyLayer policy for roll_pool. 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.
roll_pool is provided by the Dice MCP Server MCP server (patissiermongs/roleplayingmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →