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.
Cancel Training Job
lamini:cancel_training_job
Cancel a running training job. This will stop the training process.
Write
High risk
Chat Completion
lamini:chat_completion
Generate chat completions using a conversational format with message history.
Write
Medium risk
Create Dataset
lamini:create_dataset
Create a new dataset for training or fine-tuning models.
Write
Medium risk
Create Model
lamini:create_model
Create and start training a new fine-tuned model.
Write
Medium risk
Delete Dataset
lamini:delete_dataset
Permanently delete a dataset. This action cannot be undone.
Write
High risk
Delete Model
lamini:delete_model
Permanently delete a model. This action cannot be undone.
Write
High risk
Generate Text
lamini:generate_text
Generate text using a specified model with customizable parameters.
Write
Medium risk
Get Dataset
lamini:get_dataset
Fetch details about a specific dataset including size and format information.
Read
Low risk
Get Model
lamini:get_model
Fetch details about a specific model including training status and configuration.
Read
Low risk
Get Training Job
lamini:get_training_job
Fetch details about a specific training job including progress and status.
Read
Low risk
List Datasets
lamini:list_datasets
List all available datasets with optional filtering and pagination.
Read
Low risk
List Models
lamini:list_models
List all available models with optional filtering and pagination.
Read
Low risk
List Training Jobs
lamini:list_training_jobs
List all training jobs with optional filtering and pagination.
Read
Low risk