Get 5-day/3-hour forecast by city name
AI agents call get_weather_forecast to retrieve information from Multi-MCPs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and returns weather forecast data. It performs a read-only operation against a weather API (OpenWeather based on context) with no capability to modify, delete, or execute code. The blast radius of misuse is negligible — an attacker could retrieve weather data for any location but cannot cause harm to systems, data integrity, or user assets. Classification as Read is appropriate.
From the tool's definition Tool name is 'get_weather_forecast' and description states 'Get 5-day/3-hour forecast by city name' — a retrieval operation with no modification, creation, deletion, or side effects.
Attacks that exploit this kind of access
Get 5-day/3-hour forecast by city name. It is categorised as a Read tool in the Multi-MCPs MCP Server, which means it retrieves data without modifying state.
Register the Multi-MCPs MCP server in PolicyLayer and add a rule for get_weather_forecast: 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 Multi-MCPs. Nothing to install.
get_weather_forecast 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_forecast 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_forecast. 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_forecast is provided by the Multi-MCPs MCP server (taylorchen/muti-mcps). 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 →