search_fhir_resources
AI agents call search_fhir_resources to retrieve information from MCP FHIR Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve and query data without modifying it, placing this in the Read category. Severity is medium rather than low because healthcare data (FHIR resources) is sensitive; unauthorized search queries could expose Protected Health Information (PHI) depending on permissions and access controls. However, without a detailed description, confidence is moderate (0.85).
From the tool's definition Tool name 'search_fhir_resources' indicates a search operation on FHIR resources. Server description states it 'support[s] search operations'. Search is a read-only retrieval function with no side effects.
Attacks that exploit this kind of access
search_fhir_resources. It is categorised as a Read tool in the MCP FHIR Server MCP Server, which means it retrieves data without modifying state.
Register the MCP FHIR Server MCP server in PolicyLayer and add a rule for search_fhir_resources: 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 MCP FHIR Server. Nothing to install.
search_fhir_resources 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_fhir_resources 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_fhir_resources. 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_fhir_resources is provided by the MCP FHIR Server MCP server (mrosata/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 →