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

Q: How can I use Claude Code to manage Lambda Labs (GPU Cloud) from a GitHub Action?

You'll set up the claude CLI in your workflow, add the MCP Server, and then call its tools. For example, you can have one step run launchinstance and a final post-job step that always runs terminateinstances to clean up.

Q: Can I script the entire lifecycle of a Lambda Labs (GPU Cloud) instance using Claude Code?

Yes. From checking available types with listinstancetypes to creation with launchinstance and destruction with terminateinstances, you can script every step in a simple bash or Python script via Claude Code.

Q: What's the best way to list running GPUs on Lambda Labs (GPU Cloud) with Claude Code?

Run claude mcp call lambda-labs-gpu-cloud listinstances. The output is clean JSON, so you can pipe it to jq to filter or format it for any other script or command you need to run.

Q: How do I prevent accidental termination of instances?

The terminateinstances tool is powerful. In scripts, build in checks. For instance, have your script call listinstances first and confirm the instance names or tags before passing the IDs to the termination command.

Control your Lambda Labs GPU fleet from the command line. Pipe instance data directly into your shell scripts and CI/CD jobs with Claude Code.

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 Claude Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Spin Up GPUs from a Shell Script

This MCP Server connects Lambda Labs directly to your terminal. You can write a simple bash script that provisions compute on demand. No more clicking around in a web UI. Just pipe a command to Claude Code. Use `list_instance_types` to find an available `gpu_1x_h100_pcie`, then immediately call `launch_instance` with an SSH key from `list_ssh_keys`. The instance ID gets printed to stdout, ready for the next step in your script.

Automate Fleet Monitoring with Cron

You need to know the state of your machines without watching a dashboard. Set up a cron job that runs Claude Code to poll your infrastructure. It's simple, reliable, and fits right into a Linux environment. For example, `claude mcp call lambda-labs list_instances | jq '.[] | .id'` gives you a clean list of running instance IDs. You can pipe this into other tools to check status with `get_instance` and send a Slack alert if something is wrong.

Cost Control for Your CI/CD Pipelines

Don't let test instances run up your bill. Add a final cleanup step to your CI/CD configuration that calls Claude Code. It's the best way to enforce financial discipline. Just run `claude mcp call lambda-labs terminate_instances --instance_ids='...'` at the end of your workflow. The command is destructive and immediate—it vaporizes the instances and stops the billing clock. No exceptions.

Setup guide

Set up Lambda Labs (GPU Cloud) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see lambda-labs-gpu-cloud-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Lambda Labs (GPU Cloud) transactions." It will automatically discover and invoke the available Lambda Labs (GPU Cloud) tools.

Terminal

claude mcp add --transport http lambda-labs-gpu-cloud-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "lambda-labs-gpu-cloud-mcp": {
      "type": "url",
      "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 Claude Code

You'll set up the `claude` CLI in your workflow, add the MCP Server, and then call its tools. For example, you can have one step run `launch_instance` and a final post-job step that always runs `terminate_instances` to clean up.

Yes. From checking available types with `list_instance_types` to creation with `launch_instance` and destruction with `terminate_instances`, you can script every step in a simple bash or Python script via Claude Code.

Run `claude mcp call lambda-labs-gpu-cloud list_instances`. The output is clean JSON, so you can pipe it to `jq` to filter or format it for any other script or command you need to run.

The `terminate_instances` tool is powerful. In scripts, build in checks. For instance, have your script call `list_instances` first and confirm the instance names or tags before passing the IDs to the termination command.

It only processes the metadata required for the operations, like instance IDs, IP addresses, and names of your SSH keys and filesystems. The server itself is stateless and runs in a new Vinkius sandbox for each command, so nothing is ever stored.

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