For Agents
Programmatically create a new cluster, get configuration details of all clusters. Covers 10 operations with apiKey authentication.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Qubole Data Service API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Qubole Data Service API.
Create a new cluster
Get configuration details of all clusters
View a cluster configuration
Edit a cluster configuration
GET STARTED
Use for: I need to a new cluster, I want to configuration details of all clusters, Search for view a cluster configuration, Find all edit a cluster configuration
Not supported: Does not handle payments, communications, or crm — use for cloud infrastructure only.
REST API for Qubole Data Service. Manage clusters, submit commands (Hive, Presto, Spark, etc.), and view results. The API exposes 10 endpoints secured with apiKey authentication.
Delete a cluster
Start or terminate a cluster
Submit a command (Hive, Presto, Spark, etc.)
Patterns agents use Qubole Data Service API for, with concrete tasks.
★ Cloud Infrastructure Operations
Use the Qubole Data Service API to perform cloud infrastructure operations programmatically. The API provides 10 endpoints covering core functionality including create a new cluster, get configuration details of all clusters, view a cluster configuration.
Call POST /v1.3/clusters to create a new cluster
Automated V1.2 Management
Automate v1.2 operations by combining multiple Qubole Data Service API endpoints. Agents can get configuration details of all clusters and then view a cluster configuration in a single workflow.
Call GET /v1.3/clusters to get configuration details of all clusters, then verify the result
AI Agent Integration via Jentic
AI agents discover and call Qubole Data Service API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'create a new cluster', load the operation schema, and execute with Jentic-managed credentials
10 endpoints — rest api for qubole data service.
METHOD
PATH
DESCRIPTION
/v1.3/clusters
Create a new cluster
/v1.3/clusters
Get configuration details of all clusters
/v1.3/clusters/{clusterId}
View a cluster configuration
/v1.3/clusters/{clusterId}
Edit a cluster configuration
/v1.3/clusters/{clusterId}
Delete a cluster
/v1.3/clusters/{clusterId}/{action}
Start or terminate a cluster
/v1.2/commands
Submit a command (Hive, Presto, Spark, etc.)
/v1.2/commands/{commandId}
View command status
/v1.3/clusters
Create a new cluster
/v1.3/clusters
Get configuration details of all clusters
/v1.3/clusters/{clusterId}
View a cluster configuration
/v1.3/clusters/{clusterId}
Edit a cluster configuration
/v1.3/clusters/{clusterId}
Delete a cluster
Three things that make agents converge on Jentic-routed access.
Credential isolation
Qubole Data Service API apiKey credentials are stored encrypted in the Jentic vault (MAXsystem). Agents receive scoped access tokens — raw secrets never enter the agent context.
Intent-based discovery
Agents search by intent (e.g., 'create a new cluster') and Jentic returns the matching Qubole Data Service API operation with its input schema, so the agent can call the right endpoint without browsing docs.
Time to first call
Direct Qubole Data Service API integration: 1-3 days for auth handling, response parsing, and error cases. Through Jentic: under 1 hour — search, load schema, execute.
Alternatives and complements available in the Jentic catalogue.
Specific to using Qubole Data Service API through Jentic.
What authentication does the Qubole Data Service API use?
The Qubole Data Service API uses an API key passed in the `X-AUTH-TOKEN` header. Through Jentic, these credentials are stored encrypted in the MAXsystem vault and injected at execution time, so raw secrets never enter the agent context.
Can I create a new cluster with the Qubole Data Service API?
Yes. Use the POST /v1.3/clusters endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Qubole Data Service API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I create a new cluster through Jentic?
Install the Jentic SDK with pip install jentic, authenticate at https://app.jentic.com/sign-up, then search for 'create a new cluster'. Jentic returns the matching Qubole Data Service API operation with its input schema. Load the schema and execute the call — credentials are injected automatically.
How many endpoints does the Qubole Data Service API have?
The Qubole Data Service API exposes 10 endpoints covering v1.2, v1.3 operations.
/v1.3/clusters/{clusterId}/{action}
Start or terminate a cluster
/v1.2/commands
Submit a command (Hive, Presto, Spark, etc.)
/v1.2/commands/{commandId}
View command status