Retrieve all resources related to a specific patient using the FHIR $patient-everything operation
AI agents call patient_everything to retrieve information from Amazon ElastiCache Memcached MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The $patient-everything operation is a standard FHIR read operation that retrieves multiple related resources for a patient. While this is a Read operation (no modification), the severity is medium rather than low because: (1) it exposes sensitive Protected Health Information (PHI) in healthcare context, and (2) an agent with this tool could potentially access comprehensive patient records across multiple resource…
From the tool's definition Tool retrieves 'all resources related to a specific patient' using FHIR $patient-everything operation. This is a query operation that fetches and aggregates healthcare data with no side effects mentioned.
Attacks that exploit this kind of access
Retrieve all resources related to a specific patient using the FHIR $patient-everything operation. It is categorised as a Read tool in the Amazon ElastiCache Memcached MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon ElastiCache Memcached MCP Server MCP server in PolicyLayer and add a rule for patient_everything: 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 Amazon ElastiCache Memcached MCP Server. Nothing to install.
patient_everything 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 patient_everything 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 patient_everything. 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.
patient_everything is provided by the Amazon ElastiCache Memcached MCP Server MCP server (awslabs.memcached-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.