Official US National Weather Service forecast for a coordinate (US land + territories). Pass lat + lon for ~7 days of day/night periods, or hourly=true for an hourly forecast. Each period: temperature, wind, chance of precipitation, short + detailed forecast. Keyless, public domain. For active wa...
AI agents call weather.forecast to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries weather forecast data based on geographic coordinates. It has no side effects, cannot modify data, and returns publicly available information. No financial transaction occurs despite the server being pay-per-call (the tool itself performs only data retrieval). Severity is low as misuse would only retrieve weather information with no harmful blast radius.
From the tool's definition Tool retrieves forecast data from US National Weather Service API without modifying, creating, or deleting any data.
Attacks that exploit this kind of access
Official US National Weather Service forecast for a coordinate (US land + territories). Pass lat + lon for ~7 days of day/night periods, or hourly=true for an hourly forecast. Each period: temperature, wind, chance of precipitation, short + detailed forecast. Keyless, public domain. For active warnings use weather.alerts. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for 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 Mcp. Nothing to install.
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 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 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.
weather.forecast is provided by the MCP server (@2sio/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 →