Search Taiwan
AI agents call search_nhi_interpretations 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 read-only search operation against public health insurance documentation and reference materials. It retrieves information without modifying, executing, or deleting data. The sibling tools confirm the server's purpose is providing access to NHI reference data (codes, rules, statistics, clauses).
From the tool's definition Tool name 'search_nhi_interpretations' and server description indicate a search function over Taiwan's National Health Insurance reference data (ICD-10 mappings, audit indicators, semantic wiki).
Attacks that exploit this kind of access
Search Taiwan. 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 search_nhi_interpretations: 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.
search_nhi_interpretations 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_nhi_interpretations 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_nhi_interpretations. 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_nhi_interpretations 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 →