Integration · Company data
Connect Claude & ChatGPT to Databox
Ask your AI to send a set of numbers into Databox, set up a new dataset for them, or check whether yesterday's data push worked. It can list accounts, data sources and datasets, create data sources and datasets, push rows and check each ingestion. It is built for getting data into Databox, not for reading your dashboards.
Free plan, no credit card. Takes about a minute.
Try asking
“Push these weekly sales figures into the Sales dataset.”
The AI finds the dataset and pushes the rows, with your column names as keys.
“Create a data source called Webshop in the Europe/Copenhagen time zone.”
It checks the time zone name Databox accepts and creates the data source in your account.
“Set up a dataset for daily orders with date and store as the key columns.”
It creates the dataset in the data source with a title and those primary keys.
What your AI can do
Push data
Push rows into a dataset as a list of objects with column names as keys, from numbers you paste or data the AI has gathered.
Data sources and datasets
List accounts, data sources and datasets, create data sources with a time zone, and create datasets with primary keys.
Check every push
List past ingestions for a dataset and read the status and details of each one, so you know the data arrived.
“Did the last push to the Sales dataset succeed?”
It lists recent ingestions for the dataset and reads the status of the latest one.
“Which data sources and datasets do we have in Databox?”
It lists your accounts, then the data sources and the datasets in each.
“Delete the old Test dataset.”
It finds the dataset and deletes it with all its data. This cannot be undone.
10 tools for Databox
These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.
create_data_sourceChanges dataCreate a data source with a `title`, and optionally an `account_id` and IANA `timezone`, to hold your pushed datasets.create_datasetChanges dataCreate a dataset in a data source with a `title` and optional `primary_keys` (columns that uniquely identify a row).delete_datasetDeletesPermanently delete a dataset and all its data by `dataset_id`. This cannot be undone.get_ingestionGet the status and details of one data push by `dataset_id` and `ingestion_id`.list_accountsList the Databox accounts you can access. Use this to find an account ID.list_data_sourcesList the data sources in a Databox account by `account_id`.list_datasetsList the datasets in a data source by `data_source_id`.list_ingestionsList past data pushes (ingestions) to a dataset by `dataset_id`, to check they succeeded.list_timezonesList the time zone names Databox accepts for data sources.push_dataset_recordsChanges dataPush rows into a dataset by `dataset_id`; `records` is a list of objects with column names as keys.
Set up in three steps
- 1
Pick the app
Create a free PipMCP account and choose Databox from the app list.
- 2
Paste your key
Paste a Databox API key. In Databox go to your Profile page (Account Management > Profile). In the Password & Security section find API key and click Create. Only Admin users can manage API keys.
- 3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
- Click your name, then Settings › Connectors › Add custom connector.
- Paste your link as the Remote MCP server URL.
- Switch it on from the + menu in a chat.
Questions
What can the AI do in Databox?
The AI can list accounts, data sources, datasets, ingestions and accepted time zones, and read the status of a data push. It can create data sources and datasets, push rows into a dataset and delete a dataset, if you switch those tools on. It cannot read your dashboards or metrics.
Does the AI see my Databox API key?
No. Your Databox API key is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.
Can I control what the AI is allowed to do?
Yes. You choose which tools are switched on. Deleting a dataset removes it and all its data permanently, so you can keep that tool off or require your approval before it runs. Every tool call is logged.
Does it work with ChatGPT?
Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.
What does it cost?
PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Databox account.
Can the AI read my Databox dashboards?
No. The Databox API that PipMCP connects to is for pushing data in and managing data sources and datasets. The AI can send rows to Databox and check that they arrived, but it cannot read the numbers shown on your dashboards.
Related integrations
Let your AI work in Databox today.
Start free. Your key stays encrypted, and you decide what the AI may do.
Connect Databox freePipMCP is not affiliated with Databox. Product names are trademarks of their owners.