How to Use the Lambda Labs (GPU Cloud) MCP in Windsurf

Q: What happens if I ask Windsurf to terminate an instance?

It will use the terminateinstances tool, which permanently destroys the specified instance. Any data on its local drive is gone for good. This action is irreversible and stops billing immediately.

Let Windsurf's Cascade agent manage your Lambda Labs stack. Set a goal, and it'll launch, monitor, and tear down GPUs for you.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lambda Labs (GPU Cloud) MCP to Windsurf

Create your Vinkius account to connect Lambda Labs (GPU Cloud) to Windsurf and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Lambda Labs (GPU Cloud) with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision GPU Clusters Autonomously

This MCP Server gives Windsurf's Cascade agent direct control over your Lambda Labs account. Give it a goal like "get me a 4x A100 machine for training" and it gets to work. Cascade checks what's available with `list_instance_types` and finds the right box in the right region. Once it has a target, it uses `launch_instance` to spin it up, injecting the correct public key from `list_ssh_keys` so you have access the moment it boots. You don't prompt it step-by-step. You give it a destination, and it charts the course.

Keep an Eye on Your Training Runs

You need to know what's running and where. Ask Windsurf to "show me all active training instances." It uses `list_instances` to get a complete inventory of your running machines. For a specific job, you can ask for details. Cascade will use `get_instance` to pull the IP address, status, and even the SSH command you need to connect. It puts the exact info you need right in front of you.

Stop Wasting Money on Idle GPUs

Forgetting to shut down a GPU instance is an expensive mistake. With Windsurf, you just tell it "tear down the staging environment." It figures out which instances belong to that project. Then, it runs `terminate_instances` with the exact instance IDs. The machines are destroyed, and billing stops cold. It's the easiest way to make sure you're only paying for compute you're actually using.

Setup guide

Set up Lambda Labs (GPU Cloud) MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
2

Add the Lambda Labs (GPU Cloud) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Lambda Labs (GPU Cloud) payment history." If connected, Cascade will call the Lambda Labs (GPU Cloud) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "lambda-labs-gpu-cloud-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lambda Labs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Lambda Labs (GPU Cloud) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Lambda Labs (GPU Cloud) MCP in Windsurf

Windsurf's Cascade agent uses this MCP Server's tools to manage your GPU infrastructure. You give it high-level goals, and it automatically runs commands like `launch_instance` or `terminate_instances` on Lambda Labs to get the job done.

Yes. Just tell Cascade what kind of machine you need. It will use `list_instance_types` to find a match on Lambda Labs (GPU Cloud) and `launch_instance` to provision it for you, no manual steps required.

It is. Your Lambda Labs credentials are not stored or seen by the agent. Vinkius manages the connection through a single, secure token, and the server runs in an ephemeral sandbox for each operation.

It will use the `terminate_instances` tool, which permanently destroys the specified instance. Any data on its local drive is gone for good. This action is irreversible and stops billing immediately.

The server only handles data needed to manage your instances. This includes instance IDs, IP addresses, region names, and the names of your SSH keys and filesystems. Vinkius isolates every request in a zero-trust environment, so your data isn't persisted or shared.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript