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. 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 |
|---|---|
ingest_data | Ingests records into a Databox dataset, creating or updating it automatically. |
ask_genie | Runs AI-powered analysis on a dataset, translating natural questions into structured queries to produce insights. |
create_dataset | Creates a new dataset in Databox with a defined or auto-inferred schema. |
create_data_source | Creates a new data source entry to organize datasets within Databox. |
list_accounts | Lists all Databox accounts accessible with the current credentials. |
list_data_sources | Retrieves all data sources available in the current account. |
list_data_source_datasets | Lists all datasets contained within a specified data source. |
get_dataset_ingestions | Shows ingestion history for a dataset to verify when data was last added. |
delete_dataset | Deletes a specified dataset from Databox. |
delete_data_source | Deletes a data source along with all datasets it contains. |
Note: Additional tools may be added over time (for example, future versions might introduce new analysis functions). In the current release, there are 11 primary tools as listed above, offering comprehensive control. All tool calls use the MCP's JSON-RPC protocol — usually, as a developer you won't call these directly, but the AI agent will use them under the hood to fulfill your requests.