AI agents call lawink_precedent_relations 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 and retrieves relationship data from a legal knowledge graph—specifically, it explores connections between precedents (citations and similarities). It performs no creation, modification, deletion, or execution of external operations. It is purely informational retrieval, fitting the 'Read' category.
From the tool's definition Tool description explicitly indicates exploration of ontology relations: 'cites' (citations), 'similar_to' (similar precedents). The verb structure shows retrieval of existing relationships without modification.
Attacks that exploit this kind of access
특정 판례의 모든 온톨로지 관계 (인용 법령 cites, 유사 판례 similar_to,. 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_precedent_relations: 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_precedent_relations 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_precedent_relations 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_precedent_relations. 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_precedent_relations 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 →