How to Use the Lambda Labs (GPU Cloud) MCP in VS Code Copilot

Q: How do I configure Lambda Labs (GPU Cloud) for my team in VS Code Copilot?

Create a .vscode/mcp.json file in your repository root and add the server configuration. Once pushed, any team member using VS Code 1.96+ with Copilot can access the GPU tools.

Q: Can VS Code Copilot check GPU availability on Lambda Labs (GPU Cloud)?

Yes, the agent runs listinstancetypes to verify physical node availability in active regions. It will tell you if the H100 or A100 nodes are currently in stock before you try to boot one.

Q: How does VS Code Copilot handle SSH keys for Lambda Labs (GPU Cloud)?

The agent executes listsshkeys to map registered public keys. When you run launchinstance, it ensures the correct key is injected so your local VS Code remote extension can connect.

Q: Can we mount persistent NAS volumes?

Yes, the agent runs listfilesystems to discover shared storage. It can then generate the correct mount commands to attach your datasets to your new GPU nodes.

Share Lambda Labs GPU workflows via this MCP Server across your team inside VS Code Copilot Chat.

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 VS Code Copilot

Create your Vinkius account to connect Lambda Labs (GPU Cloud) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-wide GPU provisioning with `launch_instance`

`launch_instance` spins up specialized GPU nodes directly from the VS Code Copilot chat window. By committing the server configuration to your repository, every developer on your team can provision identical hardware. This eliminates configuration drift across your engineering team. This MCP tool helps Copilot translate your natural language requests into exact API calls. It ensures your team uses the correct SSH keys and instance classes for every training run.

Track active compute using this MCP Server

`list_instances` returns a live list of all active GPU virtual machines running in your Lambda Cloud account. VS Code Copilot displays this inventory in your chat pane to show which nodes are currently costing money. You can quickly spot orphaned instances that your team forgot to shut down. The agent reads the status of each machine, including its IP address and boot time. This gives your DevOps engineers immediate visibility without requiring access to the web dashboard.

Safe teardowns with `terminate_instances`

`terminate_instances` permanently destroys specified GPU nodes to stop billing immediately. VS Code Copilot prompts you for confirmation before executing this destructive action to prevent accidental data loss. It warns you that any unbacked ephemeral storage will be wiped. This team-wide integration helps control cloud spend by letting developers kill their training boxes directly from the editor. You don't have to rely on manual web console cleanups.

Setup guide

Set up Lambda Labs (GPU Cloud) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Lambda Labs (GPU Cloud) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Lambda Labs (GPU Cloud) tools listed. Try asking: "List my recent Lambda Labs (GPU Cloud) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the server configuration. Once pushed, any team member using VS Code 1.96+ with Copilot can access the GPU tools.

Yes, the agent runs `list_instance_types` to verify physical node availability in active regions. It will tell you if the H100 or A100 nodes are currently in stock before you try to boot one.

The agent executes `list_ssh_keys` to map registered public keys. When you run `launch_instance`, it ensures the correct key is injected so your local VS Code remote extension can connect.

Yes, the agent runs `list_filesystems` to discover shared storage. It can then generate the correct mount commands to attach your datasets to your new GPU nodes.

The server only processes your Lambda API keys and instance IDs to execute lifecycle commands. All authentication data is handled locally within your VS Code environment, ensuring your infrastructure credentials never leak to external logging systems.

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