AI agents call lawink_ontology_stats 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 retrieves statistical information about the ontology graph—entity counts, relation type counts, and synchronization metadata. It performs read-only queries with no ability to modify, delete, or execute code. The output is informational metadata. No side effects or blast radius from misuse.
From the tool's definition Tool name 'lawink_ontology_stats' and description '온톨로지 그래프 통계 (엔티티/관계 타입별 건수, 최근 동기 시각)' [Ontology graph statistics (counts by entity/relation types, recent sync time)] indicate retrieval of aggregate statistics and metadata about the knowledge graph…
Attacks that exploit this kind of access
온톨로지 그래프 통계 (엔티티/관계 타입별 건수, 최근 동기 시각). 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_stats: 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_stats 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_stats 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_stats. 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_stats 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 →