Databox MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add --transport http databox https://mcp.databox.com/mcp
README.md

Chat with your data. Anywhere.

Databox MCP

Chat with your data. Anywhere.

Databox MCP is a Model Context Protocol server that connects your business data to AI assistants. Ask questions about your metrics in plain English—no SQL, no dashboard building, no data exports.

Overview

Databox MCP enables AI tools like Claude, Cursor, n8n, and Gemini CLI to access and analyze your Databox data conversationally. It transforms how you interact with business metrics—instead of navigating dashboards, you simply ask questions and get instant answers.

Key Benefits:

  • Query your data using natural language
  • Works with 130+ existing Databox integrations
  • No additional cost for Databox users
  • Setup in under 60 seconds

Supported AI Clients

Client Status
Claude Desktop Supported
Claude Web Supported
Cursor Supported
n8n Supported
Gemini CLI Supported
Any MCP-compatible tool Supported

Quick Setup

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "databox": {
      "type": "http",
      "url": "https://mcp.databox.com/mcp"
    }
  }
}

Claude Web / Claude Desktop App

  1. Go to SettingsConnectors
  2. Click Add Custom Connector
  3. Enter the remote server URL: https://mcp.databox.com/mcp
  4. Complete the authorization flow

Cursor

Add the Databox MCP server in Cursor's MCP settings with the URL https://mcp.databox.com/mcp.

n8n

Use an HTTP Request node pointing to https://mcp.databox.com/mcp and build your workflows from there.

Available Tools

Databox MCP exposes 15 tools for interacting with your data:

Account Management

`list_accounts`

List all Databox accounts accessible to the authenticated user.

No parameters.


Data Sources

`list_data_sources`

List all data sources for a specific account.

Parameter Type Required Description
account_id string Yes Unique identifier of the account
`create_data_source`

Create a new data source container for organizing datasets.

Parameter Type Required Description
name string Yes Human-readable name for the data source
account_id string No Target account ID. Defaults to the account associated with the API key
`delete_data_source`

Permanently remove a data source and all its associated datasets. Cannot be undone.

Parameter Type Required Description
data_source_id string Yes Unique identifier of the data source to delete
`list_data_source_datasets`

List all datasets belonging to a specific data source.

Parameter Type Required Description
data_source_id string Yes Unique identifier of the data source

Datasets

`create_dataset`

Create a new dataset within a data source, with an optional schema.

Parameter Type Required Description
data_source_id string Yes ID of the parent data source
name string Yes Human-readable name for the dataset
columns string (JSON) No Column schema as a JSON array. Each column has name (string) and data_type ("string", "number", or "datetime")
primary_keys string (JSON) No JSON array of column names to use as composite key (e.g. '["id"]')
`ingest_data`

Push data records into an existing dataset.

Parameter Type Required Description
dataset_id string Yes Unique identifier of the target dataset (UUID)
data string (JSON) Yes JSON array of records, each an object with column names as keys
`get_dataset_ingestions`

Get ingestion history for a specific dataset.

Parameter Type Required Description
dataset_id string Yes Unique identifier of the dataset (UUID)
`get_ingestion`

Get detailed information for a specific ingestion event, including record counts and dataset metrics.

Parameter Type Required Description
dataset_id string Yes Unique identifier of the dataset (UUID)
ingestion_id string Yes Unique identifier of the ingestion event (UUID)
`delete_dataset`

Permanently remove a dataset and all its data. Cannot be undone.

Parameter Type Required Description
dataset_id string Yes Unique identifier of the dataset to delete (UUID)

Tools (10)

list_accountsList all Databox accounts accessible to the authenticated user.
list_data_sourcesList all data sources for a specific account.
create_data_sourceCreate a new data source container for organizing datasets.
delete_data_sourcePermanently remove a data source and all its associated datasets.
list_data_source_datasetsList all datasets belonging to a specific data source.
create_datasetCreate a new dataset within a data source, with an optional schema.
ingest_dataPush data records into an existing dataset.
get_dataset_ingestionsGet ingestion history for a specific dataset.
get_ingestionGet detailed information for a specific ingestion event.
delete_datasetPermanently remove a dataset and all its data.

Configuration

claude_desktop_config.json
{"mcpServers": {"databox": {"type": "http", "url": "https://mcp.databox.com/mcp"}}}

Try it

List all my available Databox accounts.
Show me the data sources for my primary account.
Create a new dataset named 'Q4 Sales' in my marketing data source.
Get the ingestion history for my website traffic dataset.

Frequently Asked Questions

What are the key features of Databox?

Query business metrics using natural language. Supports 130+ Databox integrations. Manage data sources and datasets via AI. Access ingestion history and event details. Compatible with Claude, Cursor, n8n, and Gemini CLI.

What can I use Databox for?

Quickly checking marketing performance metrics without opening dashboards. Automating the ingestion of custom business data into Databox via AI workflows. Auditing data source and dataset configurations through conversational prompts. Retrieving recent data ingestion status for troubleshooting reporting pipelines.

How do I install Databox?

Install Databox by running: Add to claude_desktop_config.json

What MCP clients work with Databox?

Databox works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Databox docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare