Tool Reference
Complete reference for every tool exposed by the xplainable MCP server. Tools are grouped by category.
Select a tool, review the sample arguments, and invoke it to see a simulated response.
Discovery & Session
list_user_teams
List all teams the authenticated user belongs to.
No parameters.
set_active_team
Set the active team for this session.
team_idstrRequired
The team ID to switch to (from list_user_teams).
select_team
Interactively select the active team for this session.
No parameters.
List all available MCP tools and their descriptions.
No parameters.
get_workflows
Get available tool workflows grouped by service with execution order.
No parameters.
Models
models_get_model
Get detailed information about a model.
model_idstrRequired
ID of the model
models_get_feature_info
Get feature information including types, health metrics, and distributions.
version_idstrRequired
ID of the model version.
models_get_model_evaluation
Get detailed evaluation metrics for a model partition.
partition_idstrRequired
ID of the model partition.
models_get_model_profile
Get the model profile showing feature contributions and decision boundaries.
version_idstrRequired
ID of the model version.
models_link_preprocessor
Link a model version to a preprocessor version.
model_version_idstrRequired
The model version ID
preprocessor_version_idstrRequired
The preprocessor version ID
models_list_model_version_partitions
List all partitions for a model version.
version_idstrRequired
ID of the model version (or "latest")
models_list_model_versions
List all versions of a model.
model_idstrRequired
ID of the model
models_list_team_models
List all models for the current team (based on API key).
No parameters.
models_refit_model
Rapidly refit an existing model with new parameters without retraining.
model_idstrRequired
ID of the existing model.
version_idstrRequired
ID of the model version to refit.
target_columnstrRequired
Name of the target column.
file_pathstrdefault: None
Path to a local CSV (same data used for training).
dataset_namestrdefault: None
Name of an xplainable public dataset.
dataset_idstrdefault: None
csv_contentstrdefault: None
Raw CSV string (for remote MCP servers).
model_typestrdefault: 'classifier'
Either "classifier" or "regressor".
featuresList[str]default: None
List of feature names to update. Defaults to all features.
preprocessor_version_idstrdefault: None
Preprocessor version ID if one was used in training.
drop_columnsList[str]default: None
Columns to drop (same as in original training).
test_sizefloatdefault: 0.2
Test split fraction (use same value as original training).
max_depthintdefault: None
New max depth (None = keep current).
min_info_gainfloatdefault: None
New min info gain (None = keep current).
min_leaf_sizefloatdefault: None
New min leaf size (None = keep current).
weightfloatdefault: None
New weight (None = keep current).
power_degreefloatdefault: None
New power degree (None = keep current).
sigmoid_exponentfloatdefault: None
New sigmoid exponent (None = keep current).
tail_sensitivityfloatdefault: None
New tail sensitivity (None = keep current).
models_train_model
Train an xplainable model on a dataset and upload it to the platform.
target_columnstrRequired
Name of the column to predict.
model_namestrRequired
Name for the uploaded model.
model_descriptionstrdefault: ''
Description for the uploaded model.
file_pathstrdefault: None
Path to a local CSV file.
dataset_namestrdefault: None
Name of an xplainable public dataset (e.g. "telco_churn").
dataset_idstrdefault: None
ID of a dataset on the xplainable platform. Use datasets_list_team_datasets to find IDs. Preferred for hosted MCP.
csv_contentstrdefault: None
Raw CSV string for when file paths aren't accessible.
model_typestrdefault: 'classifier'
Either "classifier" or "regressor".
preprocessor_version_idstrdefault: None
Optional preprocessor version ID to load and apply a fitted pipeline to the features before training.
drop_columnsList[str]default: None
Optional list of column names to exclude from features.
test_sizefloatdefault: 0.2
Fraction of data to hold out for testing (0 to 1).
max_depthintdefault: 8
Maximum depth of the model decision tree.
min_info_gainfloatdefault: 0.0001
Minimum information gain required to split.
min_leaf_sizefloatdefault: 0.0001
Minimum leaf size as a fraction of training data.
weightfloatdefault: 1.0
Model weight parameter.
power_degreefloatdefault: 1.0
Power degree parameter.
sigmoid_exponentfloatdefault: 0.0
Sigmoid exponent parameter.
tail_sensitivityfloatdefault: 1.0
Tail sensitivity parameter.
Auto-Train
autotrain_summarize_by_dataset_id
Summarize a dataset that's already on the xplainable platform.
dataset_idstrRequired
ID of the dataset on the platform
team_idstrdefault: None
Team ID (uses session team_id if not provided)
Datasets
datasets_list_datasets
List all available public datasets.
No parameters.
datasets_get_dataset_info
Get information about a specific dataset.
dataset_idstrRequired
ID of the dataset
datasets_list_team_datasets
List all datasets for a team.
team_idstrdefault: None
Optional team ID (uses session team_id if not provided)
datasets_load_dataset
Load a public dataset by name. Downloads the CSV directly from the xplainable public blob storage.
namestrRequired
Name of the dataset to load
datasets_preview_dataset_json
Preview a dataset as JSON records.
dataset_idstrRequired
ID of the dataset
rowsintdefault: 10
Number of rows to preview
datasets_upload_dataset
Upload a dataset file.
file_pathstrRequired
Path to the dataset file
namestrRequired
Name for the dataset
descriptionstrdefault: None
Optional description
team_idstrdefault: None
Optional team ID (uses session team_id if not provided)
Preprocessing
preprocessing_get_preprocessor
Get detailed information about a preprocessor.
preprocessor_idstrRequired
ID of the preprocessor
preprocessing_check_signature
Check if a preprocessor version's output schema matches expected columns.
version_idstrRequired
The version ID to check
columnsList[str]Required
Expected output column names
preprocessing_create_preprocessor_from_spec
Create a new preprocessor from a PipelineSpec dict.
namestrRequired
Name of the preprocessor
descriptionstrRequired
Description of the preprocessor
specdictRequired
PipelineSpec dict
sample_dataList[dict]default: None
Optional sample data as a list of row dicts (JSON records)
preprocessing_delete_preprocessor
Delete a preprocessor and all its versions.
preprocessor_idstrRequired
The preprocessor ID to delete
preprocessing_delete_version
Delete a preprocessor version.
version_idstrRequired
The version ID to delete
preprocessing_fit_version_from_data
Fit a preprocessor version with sample data.
version_idstrRequired
The version ID to fit
sample_dataList[dict]Required
Sample data as a list of row dicts (JSON records)
preprocessing_get_version
Get metadata for a preprocessor version.
version_idstrRequired
The version ID
List all available preprocessing transformers with their parameters.
No parameters.
preprocessing_list_preprocessors
List all preprocessors for a team.
team_idstrdefault: None
Optional team ID (uses session team_id if not provided)
preprocessing_preview_from_data
Preview pipeline transformation on sample data.
version_idstrRequired
The version ID to preview
sample_dataList[dict]Required
Sample data as a list of row dicts (JSON records)
preprocessing_update_version_from_spec
Update an existing preprocessor version with a new spec.
version_idstrRequired
ID of the version to update
specdictRequired
Updated PipelineSpec dict
sample_dataList[dict]default: None
Optional sample data as a list of row dicts (JSON records)
Deployments
deployments_activate_deployment
Activate a deployment.
deployment_idstrRequired
ID of the deployment to activate
deployments_deactivate_deployment
Deactivate a deployment.
deployment_idstrRequired
ID of the deployment to deactivate
deployments_delete_deployment
Delete a deployment.
deployment_idstrRequired
ID of the deployment to delete
deployments_deploy
Deploy a model version.
model_version_idstrRequired
ID of the model version to deploy
deployments_generate_deploy_key
Generate a deploy key for a deployment.
deployment_idstrRequired
ID of the deployment
descriptionstrdefault: ''
Description of the deploy key use case
days_until_expiryintdefault: 90
Number of days until the key expires
deployments_get_active_team_deploy_keys_count
Get count of active deploy keys for a team.
team_idstrdefault: None
Optional team ID (uses session team_id if not provided)
deployments_get_deployment_payload
Get sample payload data for a deployment.
deployment_idstrRequired
ID of the deployment
deployments_list_deploy_keys
List all deploy keys for a deployment.
deployment_idstrRequired
ID of the deployment
deployments_list_deployments
List all deployments for a team.
team_idstrdefault: None
Optional team ID (uses session team_id if not provided)
deployments_revoke_deploy_key
Revoke a deploy key for a deployment.
deployment_idstrRequired
ID of the deployment
key_idstrRequired
ID of the deploy key to revoke
Inference
inference_predict
Predicts the target column of a dataset.
filenamestrRequired
The name of the file.
model_idstrRequired
The model id.
version_idstrRequired
The version id.
thresholdfloatdefault: 0.5
The threshold for classification models.
delimiterstrdefault: ','
The delimiter of the file.
inference_stream_predictions
Stream predictions for large datasets by processing in batches.
filenamestrRequired
Path to CSV file to stream
model_idstrRequired
ID of the model
version_idstrRequired
ID of the model version
thresholdfloatdefault: 0.5
Classification threshold
delimiterstrdefault: ','
CSV delimiter
batch_sizeintdefault: 1000
Size of each batch to process
Monitors
monitors_create_monitor
Create a new monitor for a model.
model_idstrRequired
ID of the model
namestrRequired
Name of the monitor
descriptionstrdefault: ''
Description of the monitor
thresholdfloatdefault: 0.5
Decision threshold
data_source_typestrdefault: 'csv'
Data source type
schedule_typestrdefault: 'manual'
Schedule type
monitors_get_monitor
Get a monitor by ID.
monitor_idstrRequired
ID of the monitor
monitors_get_team_monitors
Get all monitors for a team.
team_idstrdefault: None
Optional team ID (uses session team_id if not provided)
monitors_get_alert_rules
Get alert rules for a monitor.
monitor_idstrRequired
ID of the monitor
monitors_delete_monitor_item
Delete a monitor item.
monitor_item_idstrRequired
ID of the monitor item
monitors_get_monitor_item
Get a specific monitor item.
monitor_item_idstrRequired
ID of the monitor item
monitors_update_monitor_description
Update the description of a monitor.
monitor_idstrRequired
ID of the monitor
descriptionstrRequired
New description
monitors_update_monitor_name
Update the name of a monitor.
monitor_idstrRequired
ID of the monitor
Reports
Return the available widget tags and their descriptions.
No parameters.
reports_create_report
Start async report generation via the wizard.
report_descriptionstrdefault: ''
is_publicbooldefault: False
widgetsList[str]default: None
modestrdefault: 'dynamic'
max_featuresintdefault: 40
constraintsdictdefault: None
audiencedictdefault: None
reports_create_report_sync
Create a report synchronously (polls until complete or timeout).
report_descriptionstrdefault: ''
is_publicbooldefault: False
widgetsList[str]default: None
modestrdefault: 'dynamic'
max_featuresintdefault: 40
constraintsdictdefault: None
audiencedictdefault: None
poll_intervalfloatdefault: 2.0
Runs
runs_create_run
Create a new training run.
team_idstrRequired
Team ID for the run
user_idstrRequired
User ID who owns the run
run_idstrdefault: None
Optional run ID (will be generated if not provided)
model_idstrdefault: None
Optional associated model ID
namestrdefault: None
Optional run name
metadatadictdefault: None
Optional metadata dictionary
runs_get_run
Get run details by ID.
run_idstrRequired
The run ID
AI Reports
gpt_explain_model
Get a natural language explanation of the model.
model_idstrRequired
ID of the model
version_idstrRequired
ID of the model version
languagestrdefault: 'en'
Language for the explanation (e.g., "en", "es", "fr")
detail_levelstrdefault: 'medium'
Level of detail ("low", "medium", "high")
gpt_generate_documentation
Generate comprehensive documentation for a model.
model_idstrRequired
ID of the model
version_idstrRequired
ID of the model version
include_technicalbooldefault: True
Include technical details
include_businessbooldefault: True
Include business context
formatstrdefault: 'markdown'
Output format ("markdown", "html", "pdf")
gpt_generate_report
Generate a GPT-powered report for a model.
model_idstrRequired
ID of the model
version_idstrRequired
ID of the model version
target_descriptionstrdefault: 'text'
Description of the target variable
project_objectivestrdefault: 'text'
Objective of the project/model
max_featuresintdefault: 15
Maximum number of features to include in report
temperaturefloatdefault: 0.7
GPT temperature parameter (0-2, higher = more creative)
Utilities
misc_health_check
Perform a comprehensive health check.
check_databasebooldefault: True
Whether to check database connectivity
check_storagebooldefault: True
Whether to check storage systems
check_computebooldefault: True
Whether to check compute resources
misc_get_version_info
Get comprehensive version information.
No parameters.
misc_load_classifier
Load a binary classification model.
model_idstrRequired
Model ID
version_idstrRequired
Version ID
modelstrdefault: None
Existing model to add partitions to
misc_load_regressor
Load a regression model.
model_idstrRequired
Model ID
version_idstrRequired
Version ID
modelstrdefault: None
Existing model to add partitions to
misc_ping_gateway
Ping the API gateway to check connectivity.
hostnamestrdefault: None
Optional hostname to ping (uses session hostname if not provided)
misc_ping_server
Ping the compute server to check connectivity.
hostnamestrdefault: None
Optional hostname to ping (uses session hostname if not provided)
