Return system alerts, optionally filtered by patient or severity level.
AI agents call get_alerts to retrieve information from MCPDischarge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing alert data from the system without creating, modifying, or deleting information. Although it accesses healthcare data (alerts, potentially including PHI context), the operation is read-only. The low severity reflects that unauthorized access to alerts could expose information but does not directly harm systems or enable financial fraud.
From the tool's definition Tool description states 'Return system alerts' with optional filtering by patient or severity level. The verb 'Return' and 'Get' pattern indicate data retrieval with no modification or deletion. No side effects mentioned.
Attacks that exploit this kind of access
Return system alerts, optionally filtered by patient or severity level. It is categorised as a Read tool in the MCPDischarge MCP Server, which means it retrieves data without modifying state.
Register the MCPDischarge MCP server in PolicyLayer and add a rule for get_alerts: 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.
get_alerts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_alerts 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 get_alerts. 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.
get_alerts 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 →