> ## Documentation Index
> Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Tool Use

> Reference for all tools exposed by the TabPFN MCP server.

The TabPFN MCP server exposes a number of tools for performing classification and regression on Prior Labs’
managed GPU infrastructure:

### `upload_dataset`

Get a secure upload URL for your dataset. We recommend this for most workflows: your data is sent directly to cloud storage instead of through the chat, so the agent can handle larger datasets without running into context limits or long execution time.

<Warning>
  Uploading the file to the URL requires a sandbox execution environment and outbound network access. Not all MCP clients support this, and some may require a paid plan.
</Warning>

This tool returns a `dataset_id` and `upload_url` - valid for 60 minutes. Call this tool separately for uploading the training set and test dataset.

#### Required Parameters

<ParamField path="filename" type="String" required>
  The filename for the dataset. Must be `train.csv` for training data or `test.csv` for test data.

  * `"train.csv"` — Training data
  * `"test.csv"` — Test data, predictions will be generated for
</ParamField>

### `fit_and_predict_from_dataset`

Fit the TabPFN model on your pre-uploaded data and generate predictions. Use this tool when you want to fit a new model from scratch.

Upload both dataset CSV files with `upload_dataset` first, then pass the two dataset IDs here.

#### Required Parameters

<ParamField path="train_dataset_id" type="String" required>
  The dataset ID you got from `upload_dataset` for your **training** CSV. That file should include all input columns plus the column you want to predict (the target).
</ParamField>

<ParamField path="test_dataset_id" type="String" required>
  The dataset ID you got from `upload_dataset` for your **test** CSV. It should have the same input columns as the training file, but not the target column.
</ParamField>

<ParamField path="target_column" type="String" required>
  The name of the target column in the training dataset — e.g. `"price"` or `"churned"`.
</ParamField>

<ParamField path="task_type" type="Literal" required>
  The type of the predictive task.

  * `"classification"` — Predict a category or class, including probability distributions
  * `"regression"` — Predict a continuous value
</ParamField>

#### Optional Parameters

<ParamField path="output_type" type="String" default="null">
  Prediction output type, default `"preds"` for classification and `"mean"` for regression.
</ParamField>

#### Returns

<ResponseField name="model_id" type="String">
  Unique ID for the fitted model. Save this value to reuse the model later with predict tools.
</ResponseField>

<ResponseField name="download_url" type="String">
  Pre-signed URL to download the full prediction results as a JSON file. Valid for 60 minutes. Use HTTP GET to retrieve.
</ResponseField>

<ResponseField name="predictions_preview" type="Object">
  Preview of the first predictions (up to 50 samples). Contains a `note` describing how many predictions are shown vs total, and a `predictions` array with the preview data. Download the full results via `download_url` for all predictions.
</ResponseField>

<ResponseField name="summary" type="Object">
  Summary statistics of the predictions, varying by task type.

  * **Classification:** `num_samples`, `class_distribution`, `mean_confidence`, `min_confidence`, `max_confidence`
  * **Regression:** `num_samples`, `mean`, `std`, `min`, `max`, `quantile_25`, `quantile_50`, `quantile_75`
</ResponseField>

### `predict_from_dataset`

Run predictions with a previously fitted model on a new test set.

Use `upload_dataset` to upload your new test dataset file, then pass that `dataset_id` and the `model_id` you got from a previous `fit_and_predict_*` call. The test CSV must have the same set of features the model was fitted on.

#### Required Parameters

<ParamField path="model_id" type="String" required>
  The model ID of the previously fitted model, from `fit_and_predict_from_dataset` or `fit_and_predict_inline`.
</ParamField>

<ParamField path="test_dataset_id" type="String" required>
  The dataset ID of the test dataset predictions will be made from.
</ParamField>

<ParamField path="task_type" type="Literal" required>
  The type of the predictive task.

  * `"classification"` — Predict a category or class, including probability distributions
  * `"regression"` — Predict a continuous value
</ParamField>

#### Optional Parameters

<ParamField path="output_type" type="String" default="null">
  Prediction output type, default `"preds"` for classification and `"mean"` for regression.
</ParamField>

#### Returns

<ResponseField name="model_id" type="String">
  Echo of the model ID used for prediction.
</ResponseField>

<ResponseField name="download_url" type="String">
  Pre-signed URL to download the full prediction results as a JSON file. Valid for 60 minutes. Use HTTP GET to retrieve.
</ResponseField>

<ResponseField name="predictions_preview" type="Object">
  Preview of the first predictions (up to 50 samples). Contains a `note` describing how many predictions are shown vs total, and a `predictions` array with the preview data. Download the full results via `download_url` for all predictions.
</ResponseField>

<ResponseField name="summary" type="Object">
  Summary statistics of the predictions, varying by task type.

  * **Classification:** `num_samples`, `class_distribution`, `mean_confidence`, `min_confidence`, `max_confidence`
  * **Regression:** `num_samples`, `mean`, `std`, `min`, `max`, `quantile_25`, `quantile_50`, `quantile_75`
</ResponseField>

### `fit_and_predict_inline`

Use this tool when you want to fit a new model from scratch. It fits on your data and immediately returns predictions for your test set, along with a `model_id` for future reuse.

<Warning>
  Best for small datasets that fit in the conversation without running into context limits.
</Warning>

#### Required Parameters

<ParamField path="X_train" type="Matrix" required>
  Training features as a 2D array where rows represent samples and columns represent features.

  * **Shape:** `(n_train_samples, n_features)`
  * **Data types:** Numeric (int/float) or categorical (string) values
  * **Flexibility:** Handles missing values, outliers, and mixed data types automatically

  <Accordion title="Example">
    ```python theme={null}
    X_train = [
      [1.5, "red", 3],
      [2.0, "blue", 4],
      [1.8, "red", 5]
    ]
    ```
  </Accordion>
</ParamField>

<ParamField path="y_train" type="Vector" required>
  Training targets as a 1D array that must align with `X_train` rows.

  * **Shape:** `(n_train_samples,)`
  * **Classification:** Class labels (e.g., `[0, 1, 0]` or `["cat", "dog", "cat"]`)
  * **Regression:** Numeric values (e.g., `[23.5, 45.2, 12.8]`)
</ParamField>

<ParamField path="X_test" type="Matrix" required>
  Test features as a 2D array for generating predictions.

  * **Shape:** `(n_test_samples, n_features)`
  * **Critical:** Must have the **same number of features** as `X_train`

  <Accordion title="Example">
    ```python theme={null}
    X_test = [
      [1.8, "red", 5],
      [2.3, "green", 2]
    ]
    ```
  </Accordion>
</ParamField>

<ParamField path="task_type" type="Literal" required>
  The type of the predictive task.

  * `"classification"` — Predict a category or class, including probability distributions
  * `"regression"` — Predict a continuous value
</ParamField>

#### Optional Parameters

<ParamField path="output_type" type="String" default="null">
  Prediction output type, default `"preds"` for classification and `"mean"` for regression.
</ParamField>

#### Returns

<ResponseField name="model_id" type="String">
  Unique ID for the fitted model. Save this value to reuse the model later with predict tools.
</ResponseField>

<ResponseField name="predictions" type="Array">
  Prediction results in the format specified by `output_type`. For classification with `"preds"`, returns a 1D array of class labels. With `"probas"`, returns a 2D array of class probabilities. For regression with `"mean"`, returns a 1D array of predicted values.
</ResponseField>

<ResponseField name="summary" type="Object">
  Summary statistics of the predictions, varying by task type.

  * **Classification:** `num_samples`, `class_distribution`, `mean_confidence`, `min_confidence`, `max_confidence`
  * **Regression:** `num_samples`, `mean`, `std`, `min`, `max`, `quantile_25`, `quantile_50`, `quantile_75`
</ResponseField>

### `predict_inline`

Generate new predictions using a previously fitted TabPFN model.

Use this tool after calling `fit_and_predict_*` to make predictions on new data using an existing model.

<Warning>
  Best for small datasets that fit in the conversation without running into context limits.
</Warning>

#### Required Parameters

<ParamField path="model_id" type="String" required>
  ID of a previously fitted model, returned from `fit_and_predict_*`.

  <Accordion title="Example">
    ```python theme={null}
    model_id = "9f1526b2-388b-4849-b965-6373d35f1a6b"
    ```
  </Accordion>
</ParamField>

<ParamField path="X_test" type="Matrix" required>
  Test features as a 2D array for generating predictions.

  * **Shape:** `(n_test_samples, n_features)`
  * **Critical:** Must have the **same number of features** the model was originally fitted on

  <Accordion title="Example">
    ```python theme={null}
    X_test = [
      [1.2, "red", 7],
      [3.4, "blue", 1]
    ]
    ```
  </Accordion>
</ParamField>

<ParamField path="task_type" type="Literal" required>
  The type of the predictive task.

  * `"classification"` — Predict a category or class, including probability distributions
  * `"regression"` — Predict a continuous value
</ParamField>

#### Optional Parameters

<ParamField path="output_type" type="String" default="null">
  Prediction output type, default `"preds"` for classification and `"mean"` for regression.
</ParamField>

#### Returns

<ResponseField name="model_id" type="String">
  Echo of the model ID used for prediction.
</ResponseField>

<ResponseField name="predictions" type="Array">
  Prediction results in the format specified by `output_type`. Same structure as `fit_and_predict_inline`.
</ResponseField>

<ResponseField name="summary" type="Object">
  Summary statistics of the predictions, varying by task type.

  * **Classification:** `num_samples`, `class_distribution`, `mean_confidence`, `min_confidence`, `max_confidence`
  * **Regression:** `num_samples`, `mean`, `std`, `min`, `max`, `quantile_25`, `quantile_50`, `quantile_75`
</ResponseField>