AI agents call get_station_detail to retrieve information from Opinet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries and returns static information about a gas station. The data returned includes business details, contact information, facility amenities, and current fuel prices. There are no side effects, no data modification, no code execution, and no financial transactions.
From the tool's definition Tool retrieves detailed station information (name, address, phone, facilities, coordinates, current prices) by station ID. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
주유소 고유 ID(UNI_ID)로 상세 정보를 조회합니다. 상호, 주소, 전화번호, 부대시설(세차/경정비/편의점/품질인증/LPG), 좌표, 제품별 현재 가격을 반환합니다. It is categorised as a Read tool in the Opinet MCP Server, which means it retrieves data without modifying state.
Register the Opinet MCP server in PolicyLayer and add a rule for get_station_detail: 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 Opinet. Nothing to install.
get_station_detail 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 get_station_detail 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 get_station_detail. 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.
get_station_detail is provided by the Opinet MCP server (kimjintak/opinet-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 →