특정 시점(연도/시행일/MST)의 조문 본문과
AI agents call get_law_article 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 historical versions of legal articles from the tax law database. It performs a lookup/fetch operation with no capacity to modify, delete, or execute external actions. The blast radius of misuse is minimal—an agent could only retrieve existing legal information. No financial, destructive, or executable operations are possible.
From the tool's definition Tool name 'get_law_article' and description indicate retrieval of specific law article text at a point in time (year/enforcement date/MST).
Attacks that exploit this kind of access
특정 시점(연도/시행일/MST)의 조문 본문과. 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 get_law_article: 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.
get_law_article 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 get_law_article 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 get_law_article. 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.
get_law_article 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 →