# Databox — how to use (mcp.ai)

Connect your Databox account and use 7 tools for analytics straight from your AI agent. Connect with your own API key. Connect your data from any tool and track it from any device. Build and share reports, monitor trends, and discover insights.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_databox?ms=1787293440000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `databox_create_data_source`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/databox`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/databox/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/databox/create/data/source` — Tool to create a new data source in Databox. Use when you need to create a logical container for datasets within a Databox account. Requires accountId, title, and timezone parameters.
  - body: { title: string, timezone: string, accountId: integer }
- `POST https://api.mcp.ai/api/databox/create/dataset` — Tool to create a new dataset in Databox data source. Use when you need to initialize a dataset with a title, data source ID, and primary keys for unique record identification.
  - body: { title: string, primaryKeys: string[], dataSourceId: integer }
- `POST https://api.mcp.ai/api/databox/delete/data/source` — Tool to delete a data source by ID in Databox. Use when you need to permanently remove a data source. This operation is irreversible and will delete all associated datasets.
  - body: { dataSourceId: integer }
- `POST https://api.mcp.ai/api/databox/delete/dataset` — Tool to delete a dataset by ID in Databox. Use when you need to permanently remove a dataset. This operation is irreversible.
  - body: { datasetId: string }
- `POST https://api.mcp.ai/api/databox/get/dataset/ingestion/status` — Tool to check the status of a specific data ingestion for a dataset. Use when you need to verify whether a data ingestion was successful by providing the dataset ID and ingestion ID returned from the 
  - body: { datasetId: string, ingestionId: string }
- `POST https://api.mcp.ai/api/databox/list/accounts` — Tool to retrieve all Databox accounts accessible to the authenticated user. Use to identify account IDs required for subsequent API operations like data source creation.
- `POST https://api.mcp.ai/api/databox/push/data/v1` — Tool to push data points to a Databox dataset using the v1 API. Use when you need to ingest data records into a specific dataset by providing the dataset ID and an array of records matching the datase
  - body: { records: object[], datasetId: string }

## Example prompts
- "What can I do in Databox?"
- "Show me a summary of my Databox account"

## More
- Page: https://mcp.ai/databox
- Agent spec (llms.txt): https://mcp.ai/databox/llms.txt
- Postman collection: https://mcp.ai/databox/postman.json