How do I connect this MCP to my AI client?

You subscribe to the MCP through Vinkius and then connect your client like Claude or Cursor with one click. You will need to provide your Vast.ai API key during setup.

What kind of GPUs can I rent?

You can search for a wide range of hardware including RTX 4090, A100, and H100 models through the search capability.

Can I use my own Docker images?

Yes. When you rent an instance, you can specify the Docker image you want to use, such as PyTorch or TensorFlow.

How do I stop being charged for an instance?

You can tell your AI agent to delete the instance as soon as your work is done. This terminates the instance and stops the billing immediately.

Do I need to use the Vast.ai website?

No. Once connected, you can perform all searches, rentals, and management tasks directly through your AI client.

How can I find a specific GPU model like an RTX 4090?

Use the search_offers capability with a query like {"gpu_name": {"eq": "RTX 4090"}}. The agent will return a list of available offers matching that hardware.

What information do I need to rent a new GPU instance?

You need an offer_id (from search results) and a Docker image name (e.g., 'pytorch/pytorch'). You can also optionally specify the disk size in GB using the rent_instance capability.

How do I stop an instance to avoid further charges?

Simply use the delete_instance capability with the specific instance_id. This will terminate the instance and release the GPU back to the marketplace.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Vastai GPU Rental Cloud API to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Deploy high-performance GPU instances through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through Vast.ai.

01
Search offers
Search the Vast.ai marketplace for specific GPU hardware. You provide a JSON query to filter for models like the RTX 4090 or H100.
02
Delete instance
Terminate an active instance on Vast.ai. Use this to stop billing as soon as your compute task finishes.
03
List instances
View all your currently active rented instances. This capability returns status, connection details, and cost information.
04
Rent instance
Rent a new GPU instance immediately. You specify an offer ID, a Docker image, and the amount of disk space needed.

Real work

What teams actually run

Rapid Model Fine-Tuning

An AI researcher asks for an H100 instance to run a training script immediately.

Automated Compute Scaling

A DevOps engineer uses the agent to deploy multiple containers for a distributed task.

Cost-Effective Data Processing

A data scientist rents a cheap RTX 4090 for a short-lived processing job and kills it when finished.

Infrastructure Auditing

A developer asks the agent to list all active instances to check current spending.

Automate a task

Put Vast.ai to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

How to monitor GPU instances

One connector, every AI

Vast.ai works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Vast.ai to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

947ms average. Fast in production.

Vast.ai is checked daily against the live service.

Daily averagePeak 1186ms

Oct 3Today

Fastest day: 724ms
Slowest day: 1186ms
14-day trend: Improving-15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Vast.ai, so you can see the experience inside your AI.

It does not authenticate your account with Vast.ai. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Vast.ai Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_FDhKvj0GzXpDt4zTlC7GXQudBJQAnkTGnbdwdCBo/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Vast.ai capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "vastai-gpu-rental-cloud-api-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_FDhKvj0GzXpDt4zTlC7GXQudBJQAnkTGnbdwdCBo/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Vast.ai in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Vast.ai owners hand off.

This MCP is built for technical professionals who need on-demand compute power without the overhead of manual cloud management.

01
AI Researchers
They hand off model training and fine-tuning tasks to the agent to spin up nodes.
02
Data Scientists
They use the agent to manage compute resources for heavy data processing.
03
DevOps Engineers
They automate the lifecycle of GPU containers and monitor infrastructure costs.

FAQ

Questions Vast.ai owners ask.

01
How do I connect this MCP to my AI client?
You subscribe to the MCP through Vinkius and then connect your client like Claude or Cursor with one click. You will need to provide your Vast.ai API key during setup.
02
What kind of GPUs can I rent?
You can search for a wide range of hardware including RTX 4090, A100, and H100 models through the search capability.
03
Can I use my own Docker images?
Yes. When you rent an instance, you can specify the Docker image you want to use, such as PyTorch or TensorFlow.
04
How do I stop being charged for an instance?
You can tell your AI agent to delete the instance as soon as your work is done. This terminates the instance and stops the billing immediately.
05
Do I need to use the Vast.ai website?
No. Once connected, you can perform all searches, rentals, and management tasks directly through your AI client.
06
How can I find a specific GPU model like an RTX 4090?
Use the search_offers capability with a query like {"gpu_name": {"eq": "RTX 4090"}}. The agent will return a list of available offers matching that hardware.
07
What information do I need to rent a new GPU instance?
You need an offer_id (from search results) and a Docker image name (e.g., 'pytorch/pytorch'). You can also optionally specify the disk size in GB using the rent_instance capability.
08
How do I stop an instance to avoid further charges?
Simply use the delete_instance capability with the specific instance_id. This will terminate the instance and release the GPU back to the marketplace.

Explore

More in Cloud Infrastructure

Connect Vast.ai to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Search offers

Delete instance

List instances

Rent instance

What teams actually run

Rapid Model Fine-Tuning

Automated Compute Scaling

Cost-Effective Data Processing

Infrastructure Auditing

Building your own app? The connector is yours to use.

Vast.ai Connector

Claude Desktop

AI Researchers

Data Scientists

DevOps Engineers

How do I connect this MCP to my AI client?

What kind of GPUs can I rent?

Can I use my own Docker images?

How do I stop being charged for an instance?

Do I need to use the Vast.ai website?

How can I find a specific GPU model like an RTX 4090?

What information do I need to rent a new GPU instance?

How do I stop an instance to avoid further charges?

Civo (Cloud-native Kubernetes Cloud Provider API) AI Connector

Modal (Serverless AI Infrastructure) AI Connector

Akash Network (Decentralized GPU & Cloud API) AI Connector

Lambda Labs (GPU Cloud) AI Connector

Suggestions

JD Cloud Infrastructure AI Connector

Clever Cloud (Developer PaaS API) AI Connector

JD Cloud / 京东云 AI Connector

CoreWeave (AI GPU Cloud) AI Connector