하위호환용: 세법해석례/질의회신 검색. 내부적으로 search_taxlaw_documents를 사용.
AI agents call search_taxlaw_interpretations to retrieve information from Taxlaw Nts without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries existing tax law interpretation data from the Korean National Tax Service database. There are no side effects, data modifications, deletions, financial transactions, or code execution. The action is purely informational—searching and returning results. This clearly fits the Read category.
From the tool's definition Tool name 'search_taxlaw_interpretations' and description indicate searching and retrieving tax law interpretations and Q&A responses ('세법해석례/질의회신 검색').
Attacks that exploit this kind of access
하위호환용: 세법해석례/질의회신 검색. 내부적으로 search_taxlaw_documents를 사용. It is categorised as a Read tool in the Taxlaw Nts MCP Server, which means it retrieves data without modifying state.
Register the Taxlaw Nts MCP server in PolicyLayer and add a rule for search_taxlaw_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 Taxlaw Nts. Nothing to install.
search_taxlaw_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_taxlaw_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_taxlaw_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_taxlaw_interpretations is provided by the Taxlaw Nts MCP server (kim-go-chon/taxlaw-nts-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 →