Connect AI agents to the Databox MCP server

Vendor MCP

The Databox MCP connector routes your AI agent's tool calls to Databox's own MCP server through Scalekit. Each user signs in to Databox once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 19 tools.

Tools: 19
What they doRead · write · destructive: 14 · 3 · 214 read3 write2 destructive
Users sign in with: OAuth
OAuth app: Scalekit's or your own

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Databox MCP connection
In AgentKit > Connections, create a Databox MCP connection. The name you give it is the connection_name your code passes. See Configure connections.
Scalekit credentials are available for Databox MCP server, so you don't need to register an OAuth app.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'databoxmcp'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Databox MCP:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'databoxmcp_get_current_datetime',
27
  toolInput: {},
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "databoxmcp"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Databox MCP:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={},
27
    tool_name="databoxmcp_get_current_datetime",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

databoxmcp_ask_genieAsk Genie, the Databox AI data analyst, to explore and analyze a dataset using natural language.Read-only
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.
Inputs
dataset_idstringrequired
No description.
questionstringrequired
No description.
thread_idstring
No description.
databoxmcp_get_current_datetimeGet the current date and time in ISO 8601 format for a given timezone.Read-only
Get Current Datetime
Get the current date and time in ISO 8601 format for a given timezone. Useful for resolving relative date expressions such as "last month" or "yesterday" before passing absolute dates to other tools.
Inputs
timezonestring
No description.
databoxmcp_get_databoard_by_idRetrieve full details for a single Databox databoard (dashboard) by its numeric ID.Read-only
Get Databoard By Id
Retrieve full details for a single Databox databoard (dashboard) by its numeric ID.
Inputs
board_idintegerrequired
No description.
databoxmcp_get_dataset_ingestionsRetrieve the full ingestion history for a dataset, including job IDs, statuses, record counts, timestamps, and any error messages.Read-only
Get Dataset Ingestions
Retrieve the full ingestion history for a dataset, including job IDs, statuses, record counts, timestamps, and any error messages.
Inputs
dataset_idstringrequired
No description.
databoxmcp_get_date_rangesResolve a JSON-encoded SimpleDateRange object (e.g.Read-only
Get Date Ranges
Resolve a JSON-encoded SimpleDateRange object (e.g. a preset range type such as "LastXDays") into concrete start and end dates.
Inputs
date_rangestringrequired
No description.
databoxmcp_get_ingestionGet detailed information for a specific ingestion event, including status, timestamps, dataset metrics, and per-record ingestion outcomes.Read-only
Get Ingestion
Get detailed information for a specific ingestion event, including status, timestamps, dataset metrics, and per-record ingestion outcomes.
Inputs
dataset_idstringrequired
No description.
ingestion_idstringrequired
No description.
databoxmcp_list_accountsList all Databox accounts accessible to the authenticated user.Read-only
List Accounts
List all Databox accounts accessible to the authenticated user. Use this to discover account IDs needed for other operations.
Inputs
This tool takes no inputs.
databoxmcp_list_data_source_datasetsList all datasets belonging to a specific Databox data source, including schema details, row counts, and metadata.Read-only
List Data Source Datasets
List all datasets belonging to a specific Databox data source, including schema details, row counts, and metadata.
Inputs
data_source_idstringrequired
No description.
databoxmcp_list_data_sourcesList all API-ingestible data sources for a specific Databox account, returning IDs, names, types, and creation timestamps.Read-only
List Data Sources
List all API-ingestible data sources for a specific Databox account, returning IDs, names, types, and creation timestamps.
Inputs
account_idstringrequired
No description.
databoxmcp_list_merged_datasetsList all merged datasets for a specific Databox account.Read-only
List Merged Datasets
List all merged datasets for a specific Databox account. Merged datasets combine data from multiple sources into a single unified dataset.
Inputs
account_idstringrequired
No description.
databoxmcp_list_metricsList all metrics available for a Databox data source, including metric keys, names, descriptions, and available dimensions.Read-only
List Metrics
List all metrics available for a Databox data source, including metric keys, names, descriptions, and available dimensions. Pass the full metric_key value unchanged to load_metric_data.
Inputs
data_source_idintegerrequired
No description.
databoxmcp_load_metric_dataRetrieve data points for a Databox metric over a date range with optional time-series granulation and dimension breakdown.Read-only
Load Metric Data
Retrieve data points for a Databox metric over a date range with optional time-series granulation and dimension breakdown. The metric_key must be the exact value returned by list_metrics.
Inputs
data_source_idintegerrequired
No description.
end_datestringrequired
No description.
metric_keystringrequired
No description.
start_datestringrequired
No description.
dimensionstring
No description.
granulation_time_unitstring
No description.
is_whole_rangeboolean
No description.default true
metric_namestring
No description.
multiplierstring
No description.
range_type_idstring
No description.
record_limitstring
No description.
databoxmcp_refresh_chart_dataFetch chart-ready data for a Databox visualization given a metric setup, date range, and visualization type (line, bar, or table), with optional filters.Read-only
Refresh Chart Data
Fetch chart-ready data for a Databox visualization given a metric setup, date range, and visualization type (line, bar, or table), with optional filters.
Inputs
date_rangestringrequired
No description.
metric_setupstringrequired
No description.
visualizationintegerrequired
No description.
filtersstring
No description.
databoxmcp_search_databoardsSearch Databox databoards (dashboards) by text query, optionally filtered by data source type or by connection/space access ID.Read-only
Search Databoards
Search Databox databoards (dashboards) by text query, optionally filtered by data source type or by connection/space access ID.
Inputs
data_source_filterstring
No description.
querystring
No description.
space_access_id_filterstring
No description.
databoxmcp_create_data_sourceCreate a new data source container in Databox for organizing datasets.Write
Create Data Source
Create a new data source container in Databox for organizing datasets. Optionally scopes the data source to a specific account; defaults to the account of the authenticated API key.
Inputs
namestringrequired
No description.
account_idstring
No description.
databoxmcp_create_datasetCreate a structured dataset within a Databox data source, optionally defining a column schema and primary keys for tabular data storage.Write
Create Dataset
Create a structured dataset within a Databox data source, optionally defining a column schema and primary keys for tabular data storage.
Inputs
data_source_idstringrequired
No description.
namestringrequired
No description.
columnsstring
No description.
primary_keysstring
No description.
databoxmcp_ingest_dataPush data records into an existing Databox dataset.Write
Ingest Data
Push data records into an existing Databox dataset. Each record must match the dataset schema; data is validated against column types and constraints before ingestion.
Inputs
datastringrequired
No description.
dataset_idstringrequired
No description.
databoxmcp_delete_data_sourcePermanently delete a data source and all its associated datasets from Databox.Destructive
Delete Data Source
Permanently delete a data source and all its associated datasets from Databox. This operation cannot be undone.
- Idempotent
Inputs
data_source_idstringrequired
No description.
databoxmcp_delete_datasetPermanently delete a dataset and all its data from Databox.Destructive
Delete Dataset
Permanently delete a dataset and all its data from Databox. This operation cannot be undone.
- Idempotent
Inputs
dataset_idstringrequired
No description.

Setup

Install the SDK

Set your credentials

Create the Databox MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Ask Genie

Inputs

Get Current Datetime

Inputs

Get Databoard By Id

Inputs

Get Dataset Ingestions

Inputs

Get Date Ranges

Inputs

Get Ingestion

Inputs

List Accounts

Inputs

List Data Source Datasets

Inputs

List Data Sources

Inputs

List Merged Datasets

Inputs

List Metrics

Inputs

Load Metric Data

Inputs

Refresh Chart Data

Inputs

Search Databoards

Inputs

Create Data Source

Inputs

Create Dataset

Inputs

Ingest Data

Inputs

Delete Data Source

Inputs

Delete Dataset

Inputs

Related: other Analytics connectors