Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.
Get Deployment
modelry:get_deployment
Fetch a single deployment by ID with status and configuration details.
Read
Low risk
Get Model
modelry:get_model
Fetch a single model by ID with metadata and configuration details.
Read
Low risk
Get Prediction
modelry:get_prediction
Retrieve details of a specific prediction by ID.
Read
Low risk
List Deployments
modelry:list_deployments
List deployments with optional filtering and search capabilities.
Read
Low risk
List Models
modelry:list_models
List models with optional filtering and search capabilities.
Read
Low risk
List Predictions
modelry:list_predictions
List predictions with optional filtering by deployment, model, status, and date range.
Read
Low risk
Create Deployment
modelry:create_deployment
Create a new deployment for a trained model.
Write
Medium risk
Create Model
modelry:create_model
Create a new model with specified configuration and metadata.
Write
Medium risk
Delete Deployment
modelry:delete_deployment
Stop and permanently delete a deployment.
Write
High risk
Delete Model
modelry:delete_model
Permanently delete a model and all its associated data.
Write
High risk
Make Prediction
modelry:make_prediction
Make a prediction using a deployed model.
Write
Medium risk
Start Deployment
modelry:start_deployment
Start a stopped deployment to begin serving predictions.
Write
Medium risk
Stop Deployment
modelry:stop_deployment
Stop a running deployment to cease serving predictions and save costs.
Write
Medium risk
Update Deployment
modelry:update_deployment
Update an existing deployment's configuration.
Write
Medium risk
Update Model
modelry:update_model
Update an existing model's metadata and configuration.
Write
Medium risk