List available patient IDs. reason: why you need this list.
AI agents call list_patients to retrieve information from Fhir Synthetic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries and returns synthetic patient identifiers without side effects. The gated write workflow architecture (propose → approve → commit) and structured audit logging noted in the server description further confirm that read tools are segregated from write/destructive actions.
From the tool's definition Tool name 'list_patients' and description 'List available patient IDs' indicate data retrieval with no modification. The required `reason` parameter suggests audit logging of access requests.
Attacks that exploit this kind of access
List available patient IDs. reason: why you need this list. It is categorised as a Read tool in the Fhir Synthetic MCP Server, which means it retrieves data without modifying state.
Register the Fhir Synthetic MCP server in PolicyLayer and add a rule for list_patients: 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 Synthetic. Nothing to install.
list_patients 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 list_patients 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 list_patients. 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.
list_patients is provided by the Fhir Synthetic MCP server (krishnakakani-github/fhir-synthetic-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 →