AI agents call lawink_ontology_graph 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 information from a legal knowledge graph—specifically exploring entity relationships, nodes, and edges. It has no indication of creating, modifying, deleting, or executing operations. The function is pure data retrieval and exploration, consistent with Read category tools like 'get', 'query', and 'search'.
From the tool's definition Tool name contains 'graph' and description states '지식그래프 조회' (knowledge graph query) focused on 'relationship neighbors (nodes+edges)' of legal entities (precedents, statutes).
Attacks that exploit this kind of access
지식그래프 조회: 판례·법령 등 엔티티 중심의 관계 이웃(노드+엣지). 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_ontology_graph: 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_ontology_graph 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_ontology_graph 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_ontology_graph. 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_ontology_graph 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 →