timestral_forecast – 1 MCP server offers this tool
What it usually takes
context_length– in 1 of 1csv_file– in 1 of 1known_covariate_columns– in 1 of 1prediction_length– in 1 of 1show_last– in 1 of 1symmetric_averaging– in 1 of 1target_columns– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Timestral-28M co.huggingface.hugging-apps/timestral Probabilistic zero-shot forecast of the series in a CSV file with Timestral-28M. The CSV may start with a timestamp column; every other numeric column can be a target. Trailing rows whose target cells are empty are treated as the future: their known-covariate values (e.g. calendar, weather forecast) condition the forecast, and their count sets the horizon when known covariates are used. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: A plot of history plus median and 10-90% / 1-99% intervals, a CSV of all 21, quantiles, and a short summary. | context_length,csv_file,known_covariate_columns,prediction_length,show_last,symmetric_averaging,target_columns | Not stated |