Send a notification message to the patient via the SMS portal.
AI agents use notify_patient 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.
This tool performs an irreversible write action—sending an SMS message—which creates a persistent communication record in the patient's communication log. While not modifying existing data structures, it generates new data (the notification itself) and triggers an external delivery system.
From the tool's definition Tool name 'notify_patient' and description 'Send a notification message to the patient via the SMS portal' indicates it creates/sends a new communication artifact (SMS message) to a patient.
Attacks that exploit this kind of access
Send a notification message to the patient via the SMS portal. 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_patient: 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_patient 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_patient 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_patient. 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_patient 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 →