AI agents call search_encounter to retrieve information from Healow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'search' combined with the context of a FHIR API server and the description indicating it retrieves encounters matching optional filters clearly indicates a read operation. No modification, deletion, or external execution is implied.
From the tool's definition Tool name is 'search_encounter' and description states 'Search Encounters for the launch patient' — this is a query/search operation with optional filters that retrieves data without modifying or deleting records.
Attacks that exploit this kind of access
Search Encounters for the launch patient. Optional status/date filters. It is categorised as a Read tool in the Healow MCP Server, which means it retrieves data without modifying state.
Register the Healow MCP server in PolicyLayer and add a rule for search_encounter: 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 Healow. Nothing to install.
search_encounter 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_encounter 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_encounter. 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_encounter is provided by the Healow MCP server (voysi-ia/healow-mcp-server). 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 →