Get historical weather observations for a specific WeatherXM station on a specific date. Use this when you already know the station ID and want to see past weather data. Note: Only recent past dates are supported (typically last few days). Future dates are not supported.
AI agents call get_historical_observations to retrieve information from WeatherXM Pro MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a data retrieval operation with no side effects. It queries historical weather records from the WeatherXM network and returns them to the caller. The limitations noted (recent dates only, no future dates) further confirm it is read-only. The blast radius of misuse is minimal—an agent could retrieve unwanted weather data but cannot modify infrastructure, trigger external actions, or cause harm.
From the tool's definition Tool description explicitly states it 'Get[s] historical weather observations' and retrieves 'past weather data' from specific stations. No modification, deletion, execution, or financial operations are described.
Attacks that exploit this kind of access
Get historical weather observations for a specific WeatherXM station on a specific date. Use this when you already know the station ID and want to see past weather data. Note: Only recent past dates are supported (typically last few days). Future dates are not supported. It is categorised as a Read tool in the WeatherXM Pro MCP Server MCP Server, which means it retrieves data without modifying state.
Register the WeatherXM Pro MCP Server MCP server in PolicyLayer and add a rule for get_historical_observations: 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 WeatherXM Pro MCP Server. Nothing to install.
get_historical_observations 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_historical_observations 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_historical_observations. 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_historical_observations is provided by the WeatherXM Pro MCP Server MCP server (oharkins/weatherxm-mcp-server). 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 →