Search for care plans (e.g., diabetes management plans)
AI agents call search_care_plans to retrieve information from FHIR MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves care plan data from a FHIR system, which is a Read operation. However, severity is elevated to 'high' because care plans contain sensitive patient clinical information (treatment strategies, medication schedules, goals) that could enable harm if an AI agent retrieves and exfiltrates care plans for unauthorized patients.
From the tool's definition Tool name 'search_care_plans' and description 'Search for care plans' indicate a retrieval operation with no modification capability. The verb 'search' is a classic Read operation that queries data without side effects.
Attacks that exploit this kind of access
Search for care plans (e.g., diabetes management plans). It is categorised as a Read tool in the FHIR MCP Server MCP Server, which means it retrieves data without modifying state.
Register the FHIR MCP Server MCP server in PolicyLayer and add a rule for search_care_plans: 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 FHIR MCP Server. Nothing to install.
search_care_plans 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 search_care_plans 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 search_care_plans. 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.
search_care_plans is provided by the FHIR MCP Server MCP server (jcafazzo/fhir-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 →