법령 적용 타임테이블 생성 — 사용자가 귀속연도를 제시한 법령·세액공제 질문의 1차 진입점. 대상 조문(들)에 대해 ① 개정 인벤토리(현행본 <개정> 꼬리표 = 그 조항을
AI agents call build_application_timetable 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.
The tool appears to build/generate a timetable showing how tax law articles apply over time based on revision history. Despite the 'build' verb, this is fundamentally a read/query operation that retrieves and organizes legislative revision data for a given tax year — no data is written, executed, or destroyed.
From the tool's definition 법령 적용 타임테이블 생성 — generates/builds a timetable of law application based on revision inventory of articles
Attacks that exploit this kind of access
법령 적용 타임테이블 생성 — 사용자가 귀속연도를 제시한 법령·세액공제 질문의 1차 진입점. 대상 조문(들)에 대해 ① 개정 인벤토리(현행본 <개정> 꼬리표 = 그 조항을. 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 build_application_timetable: 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.
build_application_timetable 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 build_application_timetable 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 build_application_timetable. 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.
build_application_timetable 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 →