Databox MCP connector for AI agents

CALL ANY TOOL

Databox MCP exposes tools for loading metric data, listing and managing data sources and datasets, ingesting records, tracking ingestion events, and running AI-powered analysis with Genie — giving agents full control over the Databox analytics lifecycle.

databoxmcp_ask_genie

Ask Genie

Ask Genie, the Databox AI data analyst, to explore and analyze a dataset using natural language. Genie can answer business questions, run SQL queries, surface trends, and provide summaries.

Parameters

Name

Type

Required

Description

dataset_id

string

Required

No description.

question

string

Required

No description.

thread_id

string

Optional

No description.

databoxmcp_create_data_source

Create Data Source

databoxmcp_create_dataset

Create Dataset

databoxmcp_delete_data_source

Delete Data Source

databoxmcp_delete_dataset

Delete Dataset

databoxmcp_get_current_datetime

Get Current Datetime

databoxmcp_get_dataset_ingestions

Get Dataset Ingestions

databoxmcp_get_ingestion

Get Ingestion

databoxmcp_ingest_data

Ingest Data

databoxmcp_list_accounts

List Accounts

databoxmcp_list_data_source_datasets

List Data Source Datasets

databoxmcp_list_data_sources

List Data Sources

databoxmcp_list_merged_datasets

List Merged Datasets

databoxmcp_list_metrics

List Metrics

databoxmcp_load_metric_data

Load Metric Data

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="databoxmcp")

mcp = MultiServerMCPClient({
    "databoxmcp": {
        "url": "https://mcp.scalekit.com/databoxmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "databoxmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/databoxmcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "databoxmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/databoxmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="databoxmcp")
# Connect to MCP at https://mcp.scalekit.com/databoxmcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Query & analyze

Copy the prompt

Copied

List all metrics available for my top data source and show me revenue trends for the past 30 days broken down by week.

Copy the prompt

Copied

Ask Genie to analyze my sales dataset and identify the top-performing product categories this quarter.

Copy the prompt

Copied

Load metric data for conversion rate over the last 90 days with daily granulation and compare it to the previous period.

Copy the prompt

Copied

What data sources do I have in my account and how many datasets does each one contain?

Ingest & manage

Copy the prompt

Copied

Create a new data source called 'Marketing Analytics' and ingest this month's campaign performance data into it.

Copy the prompt

Copied

Check the ingestion history for my revenue dataset and show me the status of the last 5 ingestion events.

Copy the prompt

Copied

Ingest these 50 records into the customer activity dataset and confirm the ingestion completed successfully.

Copy the prompt

Copied

Delete the staging dataset I created last week and confirm all its records have been removed.

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

1

Authorize

Your user connects

Databox MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Databox MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Databox MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Databox MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Databox MCP as the user or as a shared key?

Scalekit resolves a per-user credential for each call. The Databox MCP audit log shows the real user identity, not a shared service account.

Where is the Databox MCP token stored?

In Scalekit's AES-256 encrypted vault, isolated per tenant. Tokens are auto-refreshed before expiry and revocable from a single dashboard without code changes.

Can I limit what the agent is allowed to do in Databox MCP?

Pass a toolNames filter to listScopedTools. Scalekit enforces the allowed set before every API call — the agent cannot invoke tools outside the approved list.

What happens when a user revokes Databox MCP access?

The token is invalidated at the next tool call. The agent fails closed rather than falling back to a shared key. Other users are unaffected and the revocation event is logged with a timestamp.

Can the agent write or delete data in Databox, and how do I prevent unintended changes?

Yes, tools like ingest_data, create_dataset, delete_dataset, and delete_data_source perform write and destructive operations. To restrict the agent to read-only access, pass a toolNames filter to listScopedTools that includes only list and load tools. Scalekit enforces that filter before every call, so write tools are never reachable unless explicitly permitted.

Databox MCP

Tools your analytics agent reaches for on Databox MCP, scoped per user.