Skip to content
Last updated

Available Tools and Operations


Databox MCP exposes a set of tools (API methods) that the AI or client can invoke to perform various actions. These tools cover everything from data ingestion, querying, to management of datasets and metrics. They give your AI assistant full programmatic control over your Databox environment. Below is a list of the key tools available and what they do:

Tool Name Description
ask_genieRuns AI-powered analysis on a dataset, translating natural questions into structured queries to produce insights.
create_data_sourceCreates a new data source entry to organize datasets within Databox.
create_datasetCreates a new dataset in Databox with a defined or auto-inferred schema.
delete_data_sourceDeletes a data source along with all datasets it contains.
delete_datasetDeletes a specified dataset from Databox.
get_current_datetimeGet the current date and time to resolve relative date expressions like "last month" or "yesterday".
get_dataset_ingestionsShows ingestion history for a dataset to verify when data was last added.
get_ingestionGet detailed information for a specific ingestion event, including processing status and record counts.
ingest_dataIngests records into a Databox dataset, creating or updating it automatically.
list_accountsLists all Databox accounts accessible with the current credentials.
list_data_source_datasetsLists all datasets contained within a specified data source.
list_merged_datasetsLists all merged datasets available in the current account.
list_data_sourcesRetrieves all data sources available in the current account.
list_metricsLists all metrics available for a data source with their keys, names, descriptions, and dimensions.
load_metric_dataLoad data for a metric over a date range with optional dimension breakdowns and time series granulation.

The list of available tools will grow as the MCP server evolves. In practice, you won't call these tools directly — the AI agent invokes them under the hood to fulfill your requests.