AI agents call get_patient_observations 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 queries and retrieves patient observation data (vitals and lab results) from an EMR system. It performs a read-only operation with no side effects. However, the severity is medium rather than low because the data retrieved is highly sensitive protected health information (PHI), and unauthorized exposure could harm patient privacy and be used for identity theft or discrimination.
From the tool's definition Tool name and description: 'Get observations (vitals, labs) for a patient' — retrieves existing data with no modification or deletion.
Attacks that exploit this kind of access
Get observations (vitals, labs) 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_observations: 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_observations 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_observations 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_observations. 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_observations 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 →