For Agents
Provision and manage Vertex AI Workbench notebook instances — start, stop, upgrade, diagnose — across Google Cloud regions.
Get started with Notebooks API in minutes using your preferred integration method.
# Add to your MCP client config (Claude Desktop, Cursor, Windsurf)
{
"jentic": {
"url": "https://api.jentic.com/mcp",
"auth": "oauth"
}
}
# Then ask your agent:
"provision a vertex ai workbench notebook instance"
# → Jentic returns the GET /events tool with parameter schema, agent executes.What an agent can do with Notebooks API API.
Provision notebook instances with specific machine types, accelerators, and disk sizes
Start, stop, and reset running notebook VMs to control compute spend
Upgrade instance system images and rollback to prior versions when upgrades fail
Restore notebook instance state from backups taken on a defined schedule
GET STARTED
Use for: I need to provision a new GPU-backed notebook instance, Stop all idle notebook instances in a region, Upgrade a notebook instance to the latest framework image, Diagnose a notebook instance that fails to start
Not supported: Does not run notebook code, train models, or store data — use for managed notebook instance lifecycle operations only.
The Notebooks API manages Vertex AI Workbench managed notebook instances on Google Cloud. It provisions, starts, stops, upgrades, resets, and diagnoses Jupyter-based development environments backed by Compute Engine VMs with pre-installed ML frameworks. Use it to spin up GPU/TPU-equipped notebook VMs for data scientists, restore from backup, rollback to prior states, and pull diagnostic bundles when an instance misbehaves. The spec exposes 23 endpoints across regional locations.
Diagnose unhealthy instances and download diagnostic bundles for support cases
Audit instance configuration via instances:getConfig before applying changes
Patterns agents use Notebooks API API for, with concrete tasks.
★ Self-service data science environments
Provision Vertex AI Workbench notebook instances for individual data scientists with consistent ML framework images, machine types, and accelerator attachments. The API gives platform teams a programmatic surface to enforce standards — VPC, service account, encryption key — while giving users on-demand compute. Pairs naturally with policy-as-code so each new instance is created from a vetted template.
Create a notebook instance named ds-anna-gpu in us-central1-a with machine type n1-standard-8, one Tesla T4 accelerator, and a 200 GB boot disk.
Cost control through automated start/stop
Schedule notebook instance start and stop operations to reduce compute bills outside working hours. The API exposes :start, :stop, and :reset operations that fit cleanly inside Cloud Scheduler or a workflow runner. Combined with diagnostic downloads, this is enough to operate a hands-off notebook fleet for a data team.
List all notebook instances in europe-west1, filter to those whose state is ACTIVE, and POST :stop on each instance whose name ends with -dev.
Notebook image upgrades and rollback
Upgrade notebook instances to newer framework images for security patches and library updates, with the safety net of :rollback when an upgrade breaks user workflows. The API records upgrade history so an agent can detect a recent upgrade and revert it without manual intervention. Useful for platform teams that maintain a managed notebook offering.
Trigger upgrade on notebook instance ds-anna-gpu, poll the long-running operation, and execute :rollback if a follow-up health check returns FAILED.
AI agent operations on notebook fleets via Jentic
Operations agents can use Jentic to diagnose and remediate failing notebook instances — issuing intents like diagnose stuck notebook or restore from backup — and Jentic returns the matching Notebooks API operation. Credentials stay in the Jentic vault, so agents act under scoped service-account tokens with full audit trail.
Use Jentic to find the diagnose operation for a notebook instance, load its schema, and execute it on instance ds-anna-gpu, then download the resulting diagnostic bundle.
23 endpoints — the notebooks api manages vertex ai workbench managed notebook instances on google cloud.
METHOD
PATH
DESCRIPTION
/v2/{+parent}/instances
Create a notebook instance
/v2/{+name}:start
Start a stopped instance
/v2/{+name}:stop
Stop a running instance
/v2/{+name}:upgradeSystem
Upgrade the system image
/v2/{+name}:rollback
Rollback to a prior revision
/v2/{+name}:diagnose
Generate a diagnostic bundle
/v2/{+name}:restore
Restore an instance from backup
/v2/{+parent}/instances
Create a notebook instance
/v2/{+name}:start
Start a stopped instance
/v2/{+name}:stop
Stop a running instance
/v2/{+name}:upgradeSystem
Upgrade the system image
/v2/{+name}:rollback
Rollback to a prior revision
Three things that make agents converge on Jentic-routed access.
Credential isolation
Google OAuth 2.0 access tokens are minted from a service account stored in the Jentic vault (MAXsystem). Agents act under scoped, short-lived tokens — the service-account key never enters their context.
Intent-based discovery
Agents search Jentic with intents like provision gpu notebook or diagnose stuck instance and Jentic returns the matching Notebooks API operation with required scopes and input schema.
Time to first call
Direct integration: 1-2 days to wire OAuth, regional endpoints, and long-running operation polling. Through Jentic: under 30 minutes — search, load, execute.
Alternatives and complements available in the Jentic catalogue.
Vertex AI API
Vertex AI runs the training and inference jobs that notebooks orchestrate
Use Vertex AI when the agent needs to launch a training job or model deployment; use Notebooks when it needs an interactive Jupyter environment for the data scientist.
Compute Engine API
Compute Engine offers raw VMs as an alternative to managed notebook instances
Choose Compute Engine when the agent needs a generic VM with custom software; choose Notebooks when the user wants a managed Jupyter-ready environment.
BigQuery API
BigQuery is the most common data source queried from Vertex notebooks
Use BigQuery when the agent needs to fetch or write the data that the notebook user analyses; use Notebooks to manage the analysis environment itself.
Specific to using Notebooks API API through Jentic.
What authentication does the Notebooks API use?
The API uses Google OAuth 2.0 with the cloud-platform scope. Jentic mints scoped, short-lived tokens from a service account stored in its vault so agents never see raw credentials.
Can I attach a GPU to a notebook instance through this API?
Yes. Set acceleratorConfig in the instance body when calling POST /v2/{+parent}/instances; supported accelerator types follow Compute Engine's GPU SKU list for the chosen zone.
What are the rate limits for the Notebooks API?
Google Cloud enforces per-project quotas on instance create/update operations. Treat lifecycle changes as long-running — the API returns an operation, not a synchronous result, so back-off polling beats retry storms.
How do I diagnose a stuck notebook through Jentic?
Search Jentic for diagnose notebook instance, load the schema for POST /v2/{+name}:diagnose, and execute it with the diagnostic config. The returned operation eventually contains a GCS path to the diagnostic bundle.
Does this API run notebook code itself?
No — the API is a control plane for instance lifecycle. The actual Jupyter kernel runs inside the Compute Engine VM that backs the notebook instance and is reached via JupyterLab over a tunnelled HTTPS connection.
How do I rollback after a failed upgrade?
POST to /v2/{+name}:rollback with the targetSnapshot or revisionId from the prior version, then poll the returned operation until done is true.
/v2/{+name}:diagnose
Generate a diagnostic bundle
/v2/{+name}:restore
Restore an instance from backup