AI agents call get_medications_history 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 medication history from a FHIR/EMR system without modifying data. Although classified as Read (no side effects), severity is high because unauthorized access to medication history could enable harm (e.g., identifying controlled substance prescriptions, drug allergies, or sensitive treatment information) in a healthcare context with patient privacy implications.
From the tool's definition Tool name 'get_medications_history' and description 'Get patient' indicate retrieval of historical medication data.
Attacks that exploit this kind of access
Get 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_medications_history: 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_medications_history 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_medications_history 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_medications_history. 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_medications_history 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 →