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

Q: How do I add Lambda Labs (GPU Cloud) to my Cursor workspace?

Create a .cursor/mcp.json file in your project root. Add the server details and your API token under the mcpServers block. Once saved, the Cursor agent can immediately invoke the GPU management tools.

Q: Can the Cursor agent run terminateinstances on Lambda Labs (GPU Cloud)?

Yes, you can command the agent to run terminateinstances directly from the chat pane. It will destroy the specified node and stop your billing immediately.

Q: How does Cursor use Lambda Labs (GPU Cloud) to automate training?

The editor writes your training script, runs launchinstance to get a GPU, and then provides the SSH command. You can run the script on the remote node with a single terminal command.

Q: Can I manage my SSH keys?

Yes, the agent runs listsshkeys to see which public keys are registered. It uses this list to ensure your current machine has access to any new instance it provisions.

Let Cursor write your ML training scripts and launch Lambda Labs GPUs using this MCP Server.

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 Cursor

Create your Vinkius account to connect Lambda Labs (GPU Cloud) to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Code and deploy with `launch_instance`

`launch_instance` provisions a raw GPU instance directly from the Cursor agent chat while you write your PyTorch scripts. The editor sends the API call to build the node and injects your developer SSH keys automatically. You do not need to switch to a browser to start your infrastructure. This MCP integration works with Cursor's predictive editing, allowing the agent to generate Python code that matches the exact hardware specs of the newly booted machine. You get a direct terminal link inside your editor sidebar.

Inspect live nodes using this MCP Server

`get_instance` retrieves the exact IP address and active status of your remote Lambda GPU box. Cursor uses this raw connection data to configure your remote development workspace. The editor connects its terminal directly to the active node over SSH. Instead of guessing if your instance is ready, the agent polls this endpoint until the state changes to active. You can start debugging your model code on the remote GPU immediately.

Map persistent storage via `list_filesystems`

`list_filesystems` identifies all active shared NAS volumes in your Lambda account so you can mount them to your workspace. Cursor reads this storage map to help you write correct file paths in your training scripts. You avoid path errors before running your training runs. The agent suggests the exact mount points based on the returned JSON. This keeps your dataset paths consistent across multiple ephemeral GPU instances.

Setup guide

Set up Lambda Labs (GPU Cloud) MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Lambda Labs (GPU Cloud) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Lambda Labs (GPU Cloud) transactions." If the MCP tools are loaded correctly, Cursor will call the Lambda Labs (GPU Cloud) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.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 Cursor

Create a `.cursor/mcp.json` file in your project root. Add the server details and your API token under the `mcpServers` block. Once saved, the Cursor agent can immediately invoke the GPU management tools.

Yes, you can command the agent to run `terminate_instances` directly from the chat pane. It will destroy the specified node and stop your billing immediately.

The editor writes your training script, runs `launch_instance` to get a GPU, and then provides the SSH command. You can run the script on the remote node with a single terminal command.

Yes, the agent runs `list_ssh_keys` to see which public keys are registered. It uses this list to ensure your current machine has access to any new instance it provisions.

Your API tokens and SSH keys remain local within your Cursor configuration files. The editor transmits these credentials securely to the Lambda API only when executing tools, keeping your infrastructure access private.

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