행정규칙 신구법 비교 (법제처 lawService · target=admrulOldAndNew).
AI agents call compare_admin_rule_old_new 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 compares old and new versions of administrative rules (행정규칙 신구법 비교), which is a read-only operation fetching and displaying legal text differences. No data is created, modified, deleted, or executed. The blast radius of misuse is minimal as it only retrieves legal reference information.
From the tool's definition '비교' (compare) and 'admrulOldAndNew' indicate retrieval and comparison of old and new administrative rule texts
Attacks that exploit this kind of access
행정규칙 신구법 비교 (법제처 lawService · target=admrulOldAndNew). 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 compare_admin_rule_old_new: 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.
compare_admin_rule_old_new 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 compare_admin_rule_old_new 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 compare_admin_rule_old_new. 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.
compare_admin_rule_old_new 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 →