"Meteor" matching MCP servers:

Enables classifying electricity meter days as active, standby, off, or unsure from 96 fifteen-minute kWh readings plus a meter reference, with batch support for up to 31 days and model metadata. Runs fully offline as a frozen scikit-learn classifier, exposing single-day and batch classification plus model-info tools over STDIO or HTTP.

Enables retrieval of weather data and forecasts through tool calls to support solar generation and next-month electricity bill predictions.