weather_get_hourly
AI agents call weather_get_hourly to retrieve information from Weather MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves hourly weather forecast data with no ability to modify, delete, or execute arbitrary operations. It is a straightforward read operation querying weather information. Low severity because misuse (e.g., requesting excessive forecasts) would have minimal blast radius—weather data is non-sensitive and read-only.
From the tool's definition Tool name 'weather_get_hourly' combined with server description stating it 'Provides weather data including...hourly forecasts up to 7 days' indicates this retrieves weather forecast data. The server uses the free Open-Meteo API with no side effects mentioned.
Attacks that exploit this kind of access
weather_get_hourly. It is categorised as a Read tool in the Weather MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Weather MCP Server MCP server in PolicyLayer and add a rule for weather_get_hourly: 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 MCP Server. Nothing to install.
weather_get_hourly 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 weather_get_hourly 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 weather_get_hourly. 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.
weather_get_hourly is provided by the Weather MCP Server MCP server (skyloevil/weather-mcp). 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 →