법률 → 시행령 → 시행규칙 3단 위임·인용 비교 (법제처 lawService · target=thdCmp).
AI agents call get_three_tier to retrieve information from Korean Privacy Law without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches, retrieves, and compares three-tier Korean legal documents to analyze delegation and citation relationships. It is purely informational—analyzing and presenting legal text hierarchies without creating, modifying, deleting, or executing anything.
From the tool's definition Tool performs comparison operations ('비교 comparison') on legal text documents (법률→시행령→시행규칙 'law → enforcement decree → enforcement rule'). The description indicates retrieval and analysis of hierarchical legal structures from an official source (lawService).
Attacks that exploit this kind of access
법률 → 시행령 → 시행규칙 3단 위임·인용 비교 (법제처 lawService · target=thdCmp). It is categorised as a Read tool in the Korean Privacy Law MCP Server, which means it retrieves data without modifying state.
Register the Korean Privacy Law MCP server in PolicyLayer and add a rule for get_three_tier: 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 Korean Privacy Law. Nothing to install.
get_three_tier 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_three_tier 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_three_tier. 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_three_tier is provided by the Korean Privacy Law MCP server (scvcoder/korean-privacy-law-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 →