Hourly + daily weather forecast for a WGS84 point, using the MeteoSwiss ICON seamless model via Open-Meteo. Use the trailhead coordinates.
AI agents call forecast to retrieve information from Bergauf without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns weather forecast information based on geographic coordinates. It is a straightforward data retrieval operation with no capability to modify, delete, or execute arbitrary operations. The blast radius of misuse is minimal—an AI agent could only retrieve forecasts for different locations, which poses no security or operational risk.
From the tool's definition Tool retrieves weather forecast data for a given coordinate using MeteoSwiss ICON model via Open-Meteo API. The description indicates data retrieval with no side effects: 'Hourly + daily weather forecast for a WGS84 point'.
Documented attack patterns abuse exactly the kind of access forecast gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Bergauf, and nothing reaches the server without passing your rules. This is the rule we recommend for forecast:
{
"version": "1",
"default": "deny",
"tools": {
"forecast": {}
}
}forecast is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Hourly + daily weather forecast for a WGS84 point, using the MeteoSwiss ICON seamless model via Open-Meteo. Use the trailhead coordinates. It is categorised as a Read tool in the Bergauf MCP Server, which means it retrieves data without modifying state.
Register the Bergauf MCP server in PolicyLayer and add a rule for 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 Bergauf. Nothing to install.
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 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 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.
forecast is provided by the Bergauf MCP server (lailo/bergauf). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Bergauf, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Bergauf tools catalogued and risk-classified — across an index of 43,000+ MCP servers.