Chat with your data.
Anywhere.

Connect Databox to Claude, n8n, ChatGPT, or Cursor, so teams can ask questions, get answers in plain language, and take action automatically.

Get started
Works with Claude Desktop, n8n workflows, Cursor, and 100+ MCP-compatible tools

Trusted by 20,000+ teams that don't guess their numbers.

20,000+

teams using Databox

130+

Data integrations

200+

Pre-built templates

10+

MCP tools

  • Toast
  • BambooHR
  • SmartBug
  • Conair
  • Dentsu
  • Wistia
  • Avidly
  • New Breed

How Databox MCP works

Databox MCP lets your AI tool work with your performance data, securely.

How Databox MCP works
1

Connect securely

Bring data into your AI tool with MCP. Your data stays protected & access is under your control.

2

Talk to your AI

Ask your AI a question and Databox will do the math using your metrics and history.

3

Turn insights into action

Use real analysis to trigger alerts, reports, and workflows without leaving your AI tool.

Get started

A new way to work with your data.

No dashboards to build. No SQL to write. No waiting on the data team.
Your AI gives you answers the moment you ask.

ANALYZE

Your AI data analyst. On demand.

Ask AI a simple question, and it will use your real metrics, definitions, and historical context to give you insights that are accurate, explainable, and reliable enough for everyday decisions.

  • Ask questions about revenue trends, user behavior, or campaign performance
  • Get clear explanations, not just raw numbers
INGEST

Bring new data to Databox, instantly.

Push new data directly from your AI tool into Databox to get clean, structured, and ready-to-use datasets. Then build metrics you can visualize alongside your data. No pipelines or cleanup work.

  • Upload a messy CSV and ask AI to clean and standardize it
  • Pull data from an API and store it in Databox
  • Add custom internal metrics without setup
AUTOMATE

Insights turned into automated actions.

Because AI stays connected to your systems, insights can be turned into recurring summaries, updates, follow-ups, and workflows that run automatically.
Move from insights to actions, quicker.

  • Schedule recurring AI-powered analysis and reports
  • Trigger smart alerts when key metrics change
  • Automatically generate executive summaries with context

Connect with your favorite AI tool
in 60 seconds

One endpoint. Any MCP-compatible client. No complex configuration.

Claude Web & Desktop
  1. Open Settings
  2. Go to Connectors
  3. Add custom connector
  4. Add URL: https://mcp.databox.com/mcp
View Claude Setup
n8n Workflows
  1. Add "HTTP Request" node
  2. Set URL to MCP endpoint
  3. Add API key header
  4. Build your workflow
View n8n Setup
Cursor Client
  1. Configure MCP server URL
  2. Add authentication header
  3. Start using Databox tools
View Cursor Setup
Any MCP Client
  1. Configure MCP server URL
  2. Add authentication header
  3. Start using Databox tools
View MCP docs

Start chatting with your data

Works with Claude, n8n, Cursor, ChatGPT and more.

Get started

How teams use Databox MCP

Real examples of analyzing data, adding context, and automating work.

Get started quickly

Already have a Databox account?

Add to Claude config:

{
  "mcpServers": {
    "databox": {
      "type": "http",
      "url": "https://mcp.databox.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_ACCESS_TOKEN"
      }
    }
  }
}
path: ~/Library/Application Support/Claude/claude_desktop_config.json

Use the shortcut button: Add Databox MCP server to Cursor

Or add it manually:

  1. Open Cursor Settings at Cursor > Settings… > Cursor Settings
  2. Navigate to Tools & Integrations > New MCP Server
  3. Add this configuration to your mcp.json:
{
  "mcpServers": {
    "Databox": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.databox.com/mcp",
        "--allow-http"
      ]
    }
  }
}
  1. Navigate to claude.ai or open Claude desktop app
  2. Go to Settings > Connectors > Add custom connector
  3. Configure the integration:
    • Name: Databox
    • URL: https://mcp.databox.com/mcp
    • Authentication: OAuth 2.0 (follow the on-screen authorization flow)
  4. Start asking questions about your Databox data

Enable ChatGPT developer mode (if not already enabled).

Add a new MCP connector with the following configuration:

  • Name: Databox
  • URL: https://mcp.databox.com/mcp
  • Authentication: OAuth 2.0 (complete the authorization flow when prompted)
Best for: Users who want to use Databox MCP with ChatGPT's developer mode.

There are two ways to use Databox MCP with n8n:

Option 1: Using MCP Client Tool Node (Recommended for AI Agents)

  1. In your n8n workflow, add the MCP Client Tool node
  2. Configure the node:
    • SSE Endpoint: https://mcp.databox.com/mcp
    • Authentication: Select "Bearer Token"
    • Access Token: Enter your Databox OAuth token
  3. Connect the MCP Client Tool to your AI Agent node
  4. The AI agent can now query and ingest Databox data within workflows

Option 2: Direct HTTP Integration (Recommended for Data Sync)

  1. In your n8n workflow, add an HTTP Request node
  2. Configure for Databox MCP operations:
    • Method: POST
    • URL: https://mcp.databox.com/mcp
    • Authentication: Bearer Token with your Databox OAuth token
    • Body: JSON-RPC formatted requests (see Databox MCP Tools)
  3. Use this method for scheduled data ingestion, automated reporting, or multi-step workflows

For MCP-compatible clients:

  1. Configure your client to connect to https://mcp.databox.com/mcp
  2. Authenticate using OAuth 2.0 through the login screen
See docs
Create new account

Frequently Asked Questions

What is Databox MCP?

Databox MCP is a Model Context Protocol server that connects your AI tools (like Claude, n8n, or Cursor) to your Databox data. It lets you push data from any source and query your datasets using natural language—all through your AI assistant.

How is this different from uploading data to ChatGPT?

ChatGPT recalculates from scratch and guesses at context. MCP queries your actual Databox data and provides same definitions and results as your dashboard.

Which AI tools work with MCP?

Any MCP-compatible tool, such as Claude Web & Desktop, Gemini CLI, n8n Workflows, Cursor. New integrations are being added regularly.

Do I need to code?

No, just ask questions in plain language. Developers can use the API for advanced workflows.

Is my data safe?

Absolutely. All connections use secure authentication with API keys. Your data stays in your Databox account with the same security and governance you already trust. The AI only accesses data you explicitly grant permission to.

What can I do with Databox MCP?

A bunch of amazing stuff. Push data from any source (APIs, spreadsheets, databases), query datasets with natural language, automate reports, detect trends, analyze patterns, and integrate Databox into your AI workflows—all without building dashboards or writing SQL.

Can I automate reports?

Sure. Simply connect to n8n or Make to schedule queries, analyze results, and trigger actions automatically.

What data sources can I use?

Any of 130+ Databox integrations. Or, just push new data via CSV, API, or manual entry.

How is this different from using Databox dashboards?

Dashboards require manual setup and navigation. With MCP, your AI can access your data conversationally, answer ad-hoc questions instantly, and automate workflows—no dashboard building required.

Is Databox MCP included in my plan?

Databox MCP is included for all Databox users at no additional cost. You'll need a Databox account and an API key to get started.