Reverse-lookup: given a single ICD-10 code, return the Taiwan NHI 重大傷病 (major illness) categories the diagnosis may qualify for, including category name, the ICD pattern that matched, and copayment-exemption flag. Use when an agent has a diagnosis and needs to flag major-illness applicability bef...
AI agents call check_icd_for_major_illness_eligibility 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 read operation that queries a reference database to determine eligibility criteria for an existing diagnosis code. No data is created, modified, deleted, or executed. The returned information is informational only—it flags applicability for downstream use by humans during claim submission but makes no changes to any systems.
From the tool's definition Tool performs a 'reverse-lookup' query that returns NHI major illness categories and eligibility information for a given ICD-10 code.
Attacks that exploit this kind of access
Reverse-lookup: given a single ICD-10 code, return the Taiwan NHI 重大傷病 (major illness) categories the diagnosis may qualify for, including category name, the ICD pattern that matched, and copayment-exemption flag. Use when an agent has a diagnosis and needs to flag major-illness applicability before claim submission. Don. 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 check_icd_for_major_illness_eligibility: 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.
check_icd_for_major_illness_eligibility 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 check_icd_for_major_illness_eligibility 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 check_icd_for_major_illness_eligibility. 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.
check_icd_for_major_illness_eligibility 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 →