Submit Log in

Databox MCP

by Databox

Docs

Databases & Data

analyticsbusiness-datadashboardskpireporting

Summary

Chat with your live Databox metrics and dashboards from Claude, Cursor, ChatGPT, and n8n — read-only, no CSV exports.

Features

Query live Databox metrics and dashboards in natural language
Consolidated view across all connected data sources
Read-only by design — agents cannot modify your data
Remote HTTP server, bearer-token authenticated
Works with Claude, Cursor, ChatGPT, and n8n

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it, filling in the environment variables with your own values.
Restart the agent — the "Databox MCP" tools will be available.

{
  "mcpServers": {
    "databox-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.databox.com/mcp"
      ],
      "env": {
        "DATABOX_ACCESS_TOKEN": "your-databox-access-token"
      }
    }
  }
}

Claude Code

Add the server with a single CLI command.

claude mcp add databox-mcp -e DATABOX_ACCESS_TOKEN=your-databox-access-token -- npx -y mcp-remote https://mcp.databox.com/mcp

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

{
  "mcpServers": {
    "databox-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.databox.com/mcp"
      ],
      "env": {
        "DATABOX_ACCESS_TOKEN": "your-databox-access-token"
      }
    }
  }
}

Native HTTP MCP endpoint for clients with direct HTTP support (Cursor, n8n) — add with an `Authorization: Bearer <token>` header.

{
  "command": "https://mcp.databox.com/mcp",
  "args": []
}

Description

Databox MCP exposes the business metrics and dashboards you have already connected in Databox to AI tools over the Model Context Protocol. Instead of exporting a CSV or writing SQL, you ask questions in plain language — "how did paid campaigns perform last week versus the week before?" — and the agent queries your live data directly.

Because Databox already aggregates data from sources like Google Analytics, HubSpot, Stripe, Shopify, and Facebook Ads, a single MCP connection gives an agent a consolidated view across all of them rather than one integration per tool.

It is a remote, read-only HTTP MCP server at https://mcp.databox.com/mcp, authenticated with a bearer access token you generate under Databox Settings → MCP. Read-only access means an agent can analyze and report but cannot alter your dashboards or underlying data. It is included at no extra cost on Databox's paid plans and during the 14-day trial.

Related MCP Servers

MCP: Weaviate MCP Server

by Weaviate

New

Weaviate's MCP server, built into the database itself — hybrid search, schema inspection, tenant listing and batch upserts at /v1/mcp, scoped by RBAC.

Databases & Data

MCP: MCP Toolbox for Databases

by Google

New

Google's open-source MCP server for enterprise databases — one binary that fronts AlloyDB, BigQuery, Spanner, Postgres, MySQL, Oracle, MongoDB, Snowflake and more.

Databases & DataCloud & Infrastructure