세법해석례·심판례·판례 단일 문서의 현행 유효성을 자동 채점한다. ${COMPANION_NOTICE}\n호출 한 번으로: (1) 본문/메타데이터에서 인용 법조문 시점 파싱, (2) targetYear 대비 사문화 위험 신호 점수화, (3) 최종 판정(valid_current / needs_current_check / partially_outdated / likely_outdated / superseded_or_repealed / unverified) 한 줄 라벨, (4) 권장 후속 호출 큐(korean-law-mcp.searc...
AI agents call assess_doctrine_validity 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 and analyzes the current validity status of existing tax law documents (interpretations, rulings, case law) by examining their metadata and content against a target year. It returns scores and judgment labels but does not create, modify, delete, or execute external operations. The 'next-action queue' it returns are recommendations for the user/LLM to follow, not autonomous executions.
From the tool's definition Tool description states it **자동 채점한다** (automatically scores), performs **파싱** (parsing), **점수화** (scoring), and returns a **판정** (judgment/assessment) label and recommended follow-up action queue.
Attacks that exploit this kind of access
세법해석례·심판례·판례 단일 문서의 현행 유효성을 자동 채점한다. ${COMPANION_NOTICE}\n호출 한 번으로: (1) 본문/메타데이터에서 인용 법조문 시점 파싱, (2) targetYear 대비 사문화 위험 신호 점수화, (3) 최종 판정(valid_current / needs_current_check / partially_outdated / likely_outdated / superseded_or_repealed / unverified) 한 줄 라벨, (4) 권장 후속 호출 큐(korean-law-mcp.search_law/get_law_text/search_decisions + 본 MCP의 후일자 해석례 검색)를 반환. LLM은 next-action 큐를 순서대로 실행해서 답변의 채점표에 결과를 채우세요. 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 assess_doctrine_validity: 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.
assess_doctrine_validity 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 assess_doctrine_validity 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 assess_doctrine_validity. 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.
assess_doctrine_validity 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 →