RASS 鎮靜躁動評估量表 (Richmond Agitation-Sedation Scale)
AI agents invoke calculate_rass to trigger actions in Medical Calculator 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.
calculate_rass triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
RASS 鎮靜躁動評估量表 (Richmond Agitation-Sedation Scale). It is categorised as a Execute tool in the Medical Calculator MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Medical Calculator MCP Server MCP server in PolicyLayer and add a rule for calculate_rass: 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 Medical Calculator MCP Server. Nothing to install.
calculate_rass 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 calculate_rass 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 calculate_rass. 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.
calculate_rass is provided by the Medical Calculator MCP Server MCP server (u9401066/medical-calc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.