escalate_to_doctor · MCPDischarge MCP: Risk & Policy

WHAT IT DOES

What escalate_to_doctor does on MCPDischarge

AI agents invoke escalate_to_doctor to trigger actions in MCPDischarge. 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.

WHY IT NEEDS A POLICY

Why escalate_to_doctor needs a policy

This tool executes a clinical workflow action that triggers notifications and doctor involvement in patient care decisions. While not inherently destructive or financial, it initiates consequential external operations in a healthcare context where incorrect escalations could affect patient care pathways, doctor workload, and treatment decisions.

From the tool's definition Tool name 'escalate_to_doctor' and description 'Trigger doctor review/escalation for a clinical issue' indicate an action that initiates an external process (doctor notification/review workflow) whose consequences depend on context and cannot be reversed by…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

escalate_to_doctor Rate-limited

escalate_to_doctor 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "escalate_to_doctor": {
      "limits": [
        {
          "counter": "escalate_to_doctor_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCPDischarge, so you can run agents against it safely.

FAQ

Questions about escalate_to_doctor

What does the escalate_to_doctor tool do? +

Trigger doctor review/escalation for a clinical issue. It is categorised as a Execute tool in the MCPDischarge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on escalate_to_doctor? +

Register the MCPDischarge MCP server in PolicyLayer and add a rule for escalate_to_doctor: 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 MCPDischarge. Nothing to install.

What risk level is escalate_to_doctor? +

escalate_to_doctor is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit escalate_to_doctor? +

Yes. Add a rate_limit block to the escalate_to_doctor 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.

How do I block escalate_to_doctor completely? +

Set action: deny in the PolicyLayer policy for escalate_to_doctor. 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.

What MCP server provides escalate_to_doctor? +

escalate_to_doctor is provided by the MCPDischarge MCP server (prashantsingh1234/mcp_project). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.