AI agents call get_patient_conditions to retrieve information from AgentCare without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves patient medical conditions and diagnoses from FHIR/EMR systems without any apparent capability to create, modify, delete, or execute operations. While the severity is rated 'high' due to the sensitive nature of healthcare data (PHI/PII), the functional category is Read as it performs a non-destructive query operation.
From the tool's definition Tool name 'get_patient_conditions' and description 'Get medical conditions/diagnoses for a patient' indicate data retrieval with no modification capability. The verb 'Get' and the query nature of the action align with the Read category.
Attacks that exploit this kind of access
Get medical conditions/diagnoses for a patient. It is categorised as a Read tool in the AgentCare MCP Server, which means it retrieves data without modifying state.
Register the AgentCare MCP server in PolicyLayer and add a rule for get_patient_conditions: 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 AgentCare. Nothing to install.
get_patient_conditions 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_patient_conditions 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_patient_conditions. 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_patient_conditions is provided by the AgentCare MCP server (kartha-ai/agentcare-mcp). 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 →