• INVENTORY
  • IDENTITY
  • DEPLOYMENT
  • HUMAN

How to provision GPU instances with your AI

Connect Lambda Labs to your AI client to manage cloud hardware through natural language. Your agent handles the heavy lifting of searching for availability and executing launches.

Ask AI about this page

Short answer

How can I use my AI to launch GPU instances?

Your AI queries Lambda Labs for available hardware types and your existing SSH keys, then executes the launch command. You get a running virtual machine without touching a web console or CLI. This breakdown shows how your agent handles the hardware selection and deployment.

The outcomes of your request.

Where your hardware provisioning lands.

Once you give the command, your AI moves through these stages to get your hardware ready.

INVENTORY

Hardware availability

The AI checks what GPUs are actually in stock. You get a clear list of what can be launched right now.

IDENTITY

SSH key selection

Your agent identifies your saved keys. This ensures the new instance is immediately accessible to you.

DEPLOYMENT

Instance launch

The AI triggers the creation of the VM. You receive the connection details once the machine is live.

HUMAN

Manual verification

You decide which specific GPU model or configuration to use. The AI waits for your final approval before spending any credits.

The workflow

What your AI does when the request arrives.

The AI translates your intent into specific API calls to Lambda Labs.

  1. Check hardware stock

    The agent looks up all available GPU configurations to see what fits your requirements.

    list_instance_types

  2. Find your keys

    It scans your account to find the right SSH key for remote access.

    list_ssh_keys

  3. Execute the launch

    The AI sends the final command to provision the machine with your chosen specs.

    launch_instance

  4. Confirm readiness

    The agent monitors the request to ensure the instance is ready for your workload.

    launch_instance

Try it

Copy these to start.

Use these prompts to kick off your hardware provisioning.

Starting points

These are starting points. Swap out the GPU model or key name for your actual needs.

Lambda Labs Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_GornvRH1C8hhZ2KJ4gLtkhB2ck8RuwNlliqUvB8m/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Lambda Labs capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "lambda-labs-gpu-cloud-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_GornvRH1C8hhZ2KJ4gLtkhB2ck8RuwNlliqUvB8m/mcp"
    }
  }
}
Copy into chat04

  • What GPU instance types are currently available in Lambda Labs?

  • Find my SSH keys and tell me which one is named 'dev-key'.

  • Launch a new instance using the A100 type and my primary SSH key.

  • Check available hardware and prepare to launch an instance with my default key.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Lambda Labs once, then ask.

One connection links your AI to your cloud account. Your credentials stay encrypted and secure on our side.

Connect Lambda Labs to your AI

FAQ

How this task behaves.

  • 01

    Can my AI delete existing instances?

    No. This MCP only has tools to list types, list keys, and launch new instances.

  • 02

    Does the AI choose the GPU for me?

    The AI suggests what is available, but you must confirm the specific instance type before it launches.

  • 03

    Can I use this to check my monthly billing?

    No. There are no tools available to access billing or usage data.

  • 04

    Will the AI use my default SSH key automatically?

    It can, but it will first list your keys so you can verify which one to use.

  • 05

    Can the AI change the size of an already running instance?

    No. The tools are limited to launching new instances, not modifying existing ones.

  • More questions about Lambda Labs? The Connector page answers them. See everything the Lambda Labs Connector can do

Connect Lambda Labs to Claude, Cursor, ChatGPT & more