Send a notification to the attending physician via the paging system.
AI agents use notify_doctor to create or update resources in MCPDischarge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPDischarge environment.
The tool creates data (a notification message) in the paging system rather than retrieving it (Read), executing arbitrary code (Execute), or deleting anything (Destructive). While notifications can influence clinical decisions, the tool itself only writes a message; it does not execute clinical orders or move funds.
From the tool's definition Tool description states 'Send a notification' which creates a new communication artifact (a page/message) to the physician. This is a reversible write operation that modifies the state of the notification system.
Attacks that exploit this kind of access
Send a notification to the attending physician via the paging system. It is categorised as a Write tool in the MCPDischarge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPDischarge MCP server in PolicyLayer and add a rule for notify_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.
notify_doctor is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the notify_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.
Set action: deny in the PolicyLayer policy for notify_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.
notify_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.
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 →