Look up Taiwan NHI 分析審查不予支付指標 (official threshold-based audit rules where claims exceeding a percentage are denied) — returns indicator code, category, threshold, applicable specialty, monitored procedure codes, and official action description. Use when an agent needs to know whether a procedure ...
AI agents call lookup_audit_indicator to retrieve information from Opdstar Nhi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval tool that queries Taiwan NHI audit thresholds and rules. It fetches reference information (indicator codes, categories, thresholds, procedure mappings) to inform users about existing audit policies. There are no side effects, no data creation or modification, and no code execution. The tool is informational only, appropriate for medical compliance checking without actionable risk.
From the tool's definition Tool 'lookup_audit_indicator' retrieves and returns audit rule metadata: 'returns indicator code, category, threshold, applicable specialty, monitored procedure codes, and official action description.' No mutation, deletion, or external execution is performed.
Attacks that exploit this kind of access
Look up Taiwan NHI 分析審查不予支付指標 (official threshold-based audit rules where claims exceeding a percentage are denied) — returns indicator code, category, threshold, applicable specialty, monitored procedure codes, and official action description. Use when an agent needs to know whether a procedure code is under a percentage-cap audit (e.g. It is categorised as a Read tool in the Opdstar Nhi MCP Server, which means it retrieves data without modifying state.
Register the Opdstar Nhi MCP server in PolicyLayer and add a rule for lookup_audit_indicator: 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 Opdstar Nhi. Nothing to install.
lookup_audit_indicator 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 lookup_audit_indicator 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 lookup_audit_indicator. 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.
lookup_audit_indicator is provided by the Opdstar Nhi MCP server (tatsuju/opdstar-nhi-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 →