AI agents call find_patient 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 records based on demographic search criteria. While it is a read-only operation (no side effects), the severity is elevated to medium because unauthorized patient lookups could enable privacy violations (accessing sensitive healthcare data) or support downstream attacks. The confidence is high because the description unambiguously indicates search/retrieval functionality.
From the tool's definition Tool name is 'find_patient' and description states 'Search for a patient by demographics' — both indicate a query/retrieval operation with no data modification.
Attacks that exploit this kind of access
Search for a patient by demographics. 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 find_patient: 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.
find_patient 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 find_patient 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 find_patient. 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.
find_patient 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 →