Roll a d20 death saving throw for a character at 0 HP. 10+ success, nat 20 regains 1 HP, nat 1 counts as 2 failures.
AI agents invoke roll_death_save to trigger actions in Rpg. 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 deterministic dice roll mechanic and applies game-state logic (tracking successes/failures, potentially modifying HP). It triggers an external operation (the dice engine) whose result depends on runtime randomness and modifies in-game character state. Confined entirely to a game simulation context, so blast radius is low.
From the tool's definition Roll a d20 death saving throw... 10+ success, nat 20 regains 1 HP, nat 1 counts as 2 failures
Documented attack patterns abuse exactly the kind of access roll_death_save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Rpg, and nothing reaches the server without passing your rules. This is the rule we recommend for roll_death_save:
{
"version": "1",
"default": "deny",
"tools": {
"roll_death_save": {
"limits": [
{
"counter": "roll_death_save_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}roll_death_save 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.
Free to start. No card required.
Roll a d20 death saving throw for a character at 0 HP. 10+ success, nat 20 regains 1 HP, nat 1 counts as 2 failures. It is categorised as a Execute tool in the Rpg MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Rpg MCP server in PolicyLayer and add a rule for roll_death_save: 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 Rpg. Nothing to install.
roll_death_save 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_death_save 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_death_save. 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_death_save is provided by the Rpg MCP server (mnehmos/mnehmos.rpg.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Rpg, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
47 Rpg tools catalogued and risk-classified — across an index of 43,000+ MCP servers.