调用和风天气生活指数 /v7/indices/{days}，内部固定 type=0（获取全部指数），返回格式化列表（包括日期、名称、类型、等级、级别、建议）。
AI agents call get_weather_indices to retrieve information from Weather Cuhksz without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves weather-related index data (daily life indices such as comfort levels, UV index recommendations, etc.) from a third-party API and returns formatted results. It is a read-only query operation with no side effects, no code execution, no data modification, and no destructive actions.
From the tool's definition Tool queries weather life indices from QWeather API endpoint /v7/indices/{days} with type=0 to retrieve all indices.
Attacks that exploit this kind of access
调用和风天气生活指数 /v7/indices/{days}，内部固定 type=0（获取全部指数），返回格式化列表（包括日期、名称、类型、等级、级别、建议）。. It is categorised as a Read tool in the Weather Cuhksz MCP Server, which means it retrieves data without modifying state.
Register the Weather Cuhksz MCP server in PolicyLayer and add a rule for get_weather_indices: 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 Weather Cuhksz. Nothing to install.
get_weather_indices 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_weather_indices 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_weather_indices. 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_weather_indices is provided by the Weather Cuhksz MCP server (lkcy23/mcp-server-weather-cuhksz). 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 →