관측소 검색 및 실시간 수위 데이터 통합 조회 (ChatGPT 무한 반복 방지용) - 권장 도구
AI agents call get_water_info to retrieve information from HRFCO Service 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 hydrological data (water levels, precipitation, dam discharge, station locations) without creating, modifying, or deleting any information. It is a pure read operation that fetches existing observational data from the system. The mention of preventing 'infinite ChatGPT loops' confirms it is an optimized query tool with no side effects.
From the tool's definition Tool description indicates 'get_water_info' retrieves 'real-time water level data' and performs 'observatory search' with no modification or deletion capabilities mentioned.
Attacks that exploit this kind of access
관측소 검색 및 실시간 수위 데이터 통합 조회 (ChatGPT 무한 반복 방지용) - 권장 도구. It is categorised as a Read tool in the HRFCO Service MCP Server, which means it retrieves data without modifying state.
Register the HRFCO Service MCP server in PolicyLayer and add a rule for get_water_info: 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 HRFCO Service. Nothing to install.
get_water_info 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_water_info 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_water_info. 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_water_info is provided by the HRFCO Service MCP server (kwenhwang/hrfco-service). 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 →