roll_dice
AI agents invoke roll_dice to trigger actions in DM20 Protocol. 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.
A dice-rolling tool in a D&D MCP server would execute a randomized computation and return a result. It has no meaningful side effects beyond potentially logging the roll, making it low severity. Confidence is reduced due to the empty description, but the name and D&D campaign context strongly suggest a simple execution of a dice roll algorithm.
From the tool's definition Tool name 'roll_dice' implies executing a dice-rolling operation; description is empty and uninformative.
Attacks that exploit this kind of access
roll_dice. It is categorised as a Execute tool in the DM20 Protocol MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the DM20 Protocol 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 DM20 Protocol. Nothing to install.
roll_dice 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_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.
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.
roll_dice is provided by the DM20 Protocol MCP server (polloinfilzato/dm20-protocol). 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 →