Databox MCP Server

Databox MCP is a [Model Context Protocol](https://modelcontextprotocol.io/) server that connects your business data to AI assistants. Ask questions

Remote serverstreamable-httpGo

What is the Databox MCP MCP server?

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. The databox mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

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.

Its toolset

Everything the assistant can do here goes through one of these:

  • Cursor — Add the Databox MCP server in Cursor's MCP settings with the URL https://mcp.databox.com/mcp
  • list_accounts — List all Databox accounts accessible to the authenticated user
  • list_data_sources — The list_data_sources tool exposed by this server
  • create_data_source — The create_data_source tool exposed by this server
  • delete_data_source — Permanently remove a data source and all its associated datasets. Cannot be undone
  • list_data_source_datasets — The list_data_source_datasets tool exposed by this server
  • Datasets — The Datasets tool exposed by this server
  • create_dataset — Create a new dataset within a data source, with an optional schema
  • ingest_data — The ingest_data tool exposed by this server
  • get_dataset_ingestions — The get_dataset_ingestions tool exposed by this server
  • get_ingestion — Get detailed information for a specific ingestion event, including record counts and dataset metrics
  • delete_dataset — Permanently remove a dataset and all its data. Cannot be undone

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Databox MCP's toolset — Cursor, list_accounts, list_data_sources and 11 more — is a fair guide to whether it matches your workflow. It is maintained by databox; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Databox MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Databox MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the databox mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
CursorAdd the Databox MCP server in Cursor's MCP settings with the URL https://mcp.databox.com/mcp.
list_accountsList all Databox accounts accessible to the authenticated user.
list_data_sourcesThe list_data_sources tool exposed by this server.
create_data_sourceThe create_data_source tool exposed by this server.
delete_data_sourcePermanently remove a data source and all its associated datasets. Cannot be undone.
list_data_source_datasetsThe list_data_source_datasets tool exposed by this server.
DatasetsThe Datasets tool exposed by this server.
create_datasetCreate a new dataset within a data source, with an optional schema.
ingest_dataThe ingest_data tool exposed by this server.
get_dataset_ingestionsThe get_dataset_ingestions tool exposed by this server.
get_ingestionGet detailed information for a specific ingestion event, including record counts and dataset metrics.
delete_datasetPermanently remove a dataset and all its data. Cannot be undone.
list_merged_datasetsList all merged datasets for a specific account. Merged datasets combine data from multiple sources.
MetricsThe Metrics tool exposed by this server.

How to install the Databox MCP MCP server

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

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Databox MCP to Cursor.
  • Use Databox MCP to list accounts.
  • Use Databox MCP to list data sources.

Frequently asked questions

It connects Databox MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Cursor, list_accounts, list_data_sources, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Databox MCP directly.