AI agents call lawink_statute_semantic_search to retrieve information from Lawink without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a legal knowledge graph to semantically search statute provisions. Semantic search is fundamentally a read operation that retrieves and ranks relevant data based on semantic similarity, with no capability to modify, delete, execute, or perform financial operations. The warning label reinforces its passive nature as a supplementary lookup tool.
From the tool's definition Tool performs 'semantic search' on statute provisions (법령 조문 직접 시맨틱 검색), which retrieves matching legal documents without modification or execution capabilities.
Attacks that exploit this kind of access
⚠️[보조·실험적 — 변호사 업무용 1차 도구로 쓰지 말 것] 법령 조문 직접 시맨틱 검색. It is categorised as a Read tool in the Lawink MCP Server, which means it retrieves data without modifying state.
Register the Lawink MCP server in PolicyLayer and add a rule for lawink_statute_semantic_search: 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 Lawink. Nothing to install.
lawink_statute_semantic_search 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 lawink_statute_semantic_search 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 lawink_statute_semantic_search. 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.
lawink_statute_semantic_search is provided by the Lawink MCP server (ntriq/lawink-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 →