Make a skill check against a DC with a d20 roll plus modifier.
AI agents invoke roll_check to trigger actions in Dice Roller MCP Server. 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.
This tool executes a randomized dice roll operation and applies game logic (modifier addition, DC comparison). It has no data persistence, financial, or destructive implications. The Execute category fits because it performs a computation/operation rather than simply reading stored data. Severity is low as the blast radius of misuse is negligible — it only produces a random number result.
From the tool's definition 'Make a skill check against a DC with a d20 roll plus modifier' — triggers a dice roll operation (execution of random number generation and comparison logic)
Attacks that exploit this kind of access
Make a skill check against a DC with a d20 roll plus modifier. It is categorised as a Execute tool in the Dice Roller MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Dice Roller MCP Server MCP server in PolicyLayer and add a rule for roll_check: 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 Roller MCP Server. Nothing to install.
roll_check is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the roll_check 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_check. 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_check is provided by the Dice Roller MCP Server MCP server (ltcg-addict/dice-roller). 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 →