Search for patients by phone number.
AI agents call search_patients_by_phone 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 patient records based on phone number criteria. While it is a Read operation (no data modification), the severity is elevated to medium because it enables identification and access to protected health information (PHI) about patients, which could facilitate unauthorized disclosure or targeting of individuals if misused by an AI agent.
From the tool's definition Tool name is 'search_patients_by_phone' and description states 'Search for patients by phone number.' This is a query/search operation with no modification or deletion of data.
Attacks that exploit this kind of access
Search for patients by phone number. 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_patients_by_phone: 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_patients_by_phone 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_patients_by_phone 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_patients_by_phone. 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_patients_by_phone 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 →