자연어 수문 정보 조회 (실제 코드 포함)
AI agents call get_water_info_by_location 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 retrieves hydrological data (water levels, precipitation, dam discharge) based on location input. It performs read-only queries of existing hydrological information with no capability to modify, delete, or execute arbitrary operations. The note about actual code ('실제 코드 포함') refers to retrieving code or data, not executing arbitrary code.
From the tool's definition Tool name contains 'get_water_info' and description indicates '조회' (query/retrieval). The phrase '자연어 수문 정보 조회' translates to 'natural language hydrological information query/retrieval', indicating data retrieval without modification.
Attacks that exploit this kind of access
자연어 수문 정보 조회 (실제 코드 포함). 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_by_location: 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_by_location 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_by_location 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_by_location. 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_by_location 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 →