Aggregate dispute-resolution statistics for Taiwan NHI claim disputes, broken down by category and (optionally) review stage — returns category counts and rough win-rate signals only, never individual case details, case numbers, or arguments. Use when an agent is helping a clinician understand th...
AI agents call lookup_appeal_statistics_by_category 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 tool retrieves and queries aggregated, anonymized dispute-resolution statistics. It has no side effects, does not modify data, does not execute operations, and does not delete or move money. The emphasis on 'never individual case details' further confirms it is a safe read-only data retrieval function suitable for helping clinicians understand general trends in claim disputes.
From the tool's definition Tool description explicitly states it returns 'category counts and rough win-rate signals only, never individual case details, case numbers, or arguments.' It aggregates statistics without exposing sensitive case information or enabling modifications.
Attacks that exploit this kind of access
Aggregate dispute-resolution statistics for Taiwan NHI claim disputes, broken down by category and (optionally) review stage — returns category counts and rough win-rate signals only, never individual case details, case numbers, or arguments. Use when an agent is helping a clinician understand the general dispute landscape (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_appeal_statistics_by_category: 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_appeal_statistics_by_category 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_appeal_statistics_by_category 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_appeal_statistics_by_category. 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_appeal_statistics_by_category 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 →