tabpfn_3_5_demo_run_tabpfn – 1 MCP server offers this tool
What it usually takes
builtin– in 1 of 1file– in 1 of 1n_estimators– in 1 of 1target_col– in 1 of 1test_size– 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? |
|---|---|---|
TabPFN-3.5 — Tabular Foundation Model co.huggingface.hugging-apps/tabpfn-3-5-demo Train TabPFN-3.5 on your tabular data and evaluate on a held-out split. Upload a CSV or select a built-in dataset, pick the target column, and TabPFN-3.5 fits in a single forward pass - no gradient descent and no hyperparameters. Returns test-split predictions with per-class probabilities (classification) or predicted values (regression), a confusion matrix (classification), and headline metrics. 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 | builtin,file,n_estimators,target_col,test_size | Not stated |