주변 관측소 추천 (실제 코드 포함)
AI agents call recommend_nearby_stations 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 and recommends observational station data based on geographic proximity. It has no side effects—it does not create, modify, delete, or execute external operations. It falls clearly into the Read category as a data retrieval function. The severity is low because misuse (e.g., recommending incorrect stations) would have minimal security impact in a hydrological information service context.
From the tool's definition Tool name 'recommend_nearby_stations' and description indicating it recommends nearby observation stations.
Attacks that exploit this kind of access
주변 관측소 추천 (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 recommend_nearby_stations: 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.
recommend_nearby_stations 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 recommend_nearby_stations 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 recommend_nearby_stations. 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.
recommend_nearby_stations 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 →