• DATASET
  • METRICS
  • HUMAN
  • LOGS

How to push custom metrics to Databox with your AI

Connect your data source once. After that, your AI handles the heavy lifting of formatting and sending records to your dashboards.

Ask AI about this page

Short answer

How can I send custom data to Databox using AI?

You tell your AI to take specific data points and send them to Databox. It creates the necessary datasets and pushes the raw JSON records directly into them. This keeps your dashboards updated without manual exports.

Where your data lands.

Data destinations and outcomes.

The AI maps your raw information to specific Databox structures.

DATASET

New datasets created

The AI uses the available tools to set up a fresh container for your metrics. This gives you a clean place to store new types of data.

METRICS

Live dashboard updates

Your JSON records land in Databox as active metrics. This triggers the updates you see on your visual reports.

HUMAN

Manual data review

You decide which specific JSON objects are ready for the dashboard. The AI won't push data until you confirm the structure is right.

LOGS

Data integrity check

You can ask the AI to verify the data it just sent. This ensures the records match your expected schema before you rely on the dashboard.

The workflow

What your AI does when data arrives.

The AI acts as the bridge between your raw information and your Databox account.

  1. Setup the target

    The AI prepares a destination for your incoming information by establishing a new dataset in Databox.

    create_dataset

  2. Format the records

    Your agent takes your raw text or JSON and cleans it up so Databox can read it.

    push_metrics_data

  3. Execute the push

    The AI sends the formatted data packets directly to the specific dataset you identified.

    push_metrics_data

  4. Confirm delivery

    The AI checks that the transmission was successful so you know your dashboard is current.

    push_metrics_data

Try it

Copy these to start.

Use these prompts to trigger the Databox tools.

Starting points

Swap out the bracketed text with your actual dataset names or JSON snippets.

Databox Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_m5wxPLxA4DZzlEAGQvVBd7mHBeJdKwSaNPtHchcU/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Databox capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "databox-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_m5wxPLxA4DZzlEAGQvVBd7mHBeJdKwSaNPtHchcU/mcp"
    }
  }
}
Copy into chat04

  • Create a new Databox dataset called 'Website Conversion Rates' for my marketing data.

  • Push this JSON record to my 'Monthly Sales' dataset: {"revenue": 5000, "date": "2023-10-01"}.

  • I have a list of user engagement metrics. Can you create a dataset for them and push the data?

  • Take the data from this CSV and push it to my Databox 'Inventory' dataset.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Databox once, then ask.

Click the link to authorize the connection. Your credentials stay encrypted and secure, and you can find the full tool list on the main Connector page.

Connect Databox to your AI

FAQ

How this task behaves.

  • 01

    Can the AI delete existing datasets in Databox?

    No. The AI can only create new datasets and push data to them.

  • 02

    Will the AI automatically pull data from my other apps?

    No. The AI only pushes data that you provide to it in the chat or via your connected files.

  • 03

    Does the AI handle the dashboard visualization?

    No. The AI pushes the data to Databox. You still use the Databox interface to build and style your actual charts and graphs.

  • 04

    Can I push data to an existing dataset?

    Yes. Once the dataset exists, you can tell the AI to push new metrics to it.

  • 05

    Do I need to format the JSON myself?

    You can provide raw data, and the AI will handle the formatting required by the tool to ensure it lands correctly.

  • More questions about Databox? The Connector page answers them. See everything the Databox Connector can do

Connect Databox to Claude, Cursor, ChatGPT & more