get_patient_encounters
AI agents call get_patient_encounters 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 encounter records for patients—clinical visit history—which is sensitive healthcare information. While it is read-only with no side effects, the severity is high because encounters contain Protected Health Information (PHI) including diagnoses, treatments, providers, and dates. Unauthorized access could expose sensitive medical histories.
From the tool's definition Tool name 'get_patient_encounters' indicates retrieval of encounter records. The server description confirms this is for accessing healthcare data from FHIR APIs.
Attacks that exploit this kind of access
get_patient_encounters. 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 get_patient_encounters: 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.
get_patient_encounters 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_encounters 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_encounters. 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_encounters is provided by the FHIR MCP Server MCP server (sdesani/mcp-fhir). 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 →