list_accountsLABSCO SUMMARY
Your metrics answer questions instead of rendering charts.
Databox already collects the numbers; the gap was that reading them meant building a dashboard first. Asking directly skips that, and the ingest side means an agent can put data in as well as take it out.
What it is
A remote MCP server run by Databox at https://mcp.databox.com/mcp. It connects the metrics already flowing through your Databox account — from whichever of its integrations you have connected — to any MCP client, and can create data sources and ingest data as well as read it.
What you get
- Every Databox account your login can reach, listed
- The data sources in an account, listed
- A new data source container created for organising datasets
- The datasets under a data source, listed
- A dataset created, with primary keys where the data needs them
- Data ingested into a dataset
- A data source deleted
Requirements
A Databox account — authorisation happens in the client rather than through a config file, and there is no additional charge for Databox users. Add https://mcp.databox.com/mcp as an HTTP connector: Claude Desktop takes it in claude_desktop_config.json with "type": "http", Claude Web takes it under Settings → Connectors → Add Custom Connector, and Cursor and n8n take the same URL.
Setup effort
Paste a URL — add the endpoint to your client
USE CASES
01
Finding your way around a Databox you did not set up
List the accounts you can reach, then the data sources inside the one you mean.
02
Seeing what data is actually available
List the datasets under a data source before writing a question about them.
03
Getting a new metric into Databox
Create the data source, create the dataset with its primary keys, then ingest the rows.
04
Keeping a dataset current
Push new rows into the existing dataset rather than rebuilding it.
05
Cleaning up an account that has accumulated sources
List what is there and delete the containers nothing feeds any more.
15 tools
Listed in project docs. Your client may show a different list.
list_data_sourcescreate_data_sourcedelete_data_sourcelist_data_source_datasetscreate_datasetingest_dataget_dataset_ingestionsget_ingestiondelete_datasetlist_merged_datasetslist_metricsload_metric_dataask_genieget_current_datetimeBEFORE YOU INSTALL
What to know first
Tools you get
15 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Add the endpoint to your client.
Server setup
ENDPOINT URL
https://mcp.databox.com/mcpMCP Clients
Claude.ai
Settings -> Connectors -> Add Custom Connector -> https://mcp.databox.com/mcp
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.
