How to Use the Vast.ai (GPU Rental Cloud API) MCP in Claude Code

Q: Can I build a complete deployment pipeline using Vast.ai (GPU Rental Cloud API) in Claude Code?

Yes. You write a shell script that first executes searchoffers, captures the output, and then pipes it to a tool that calls rentinstance. It's all linear, headless execution.

Automate GPU resource provisioning in CI/CD pipelines 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 Vast.ai (GPU Rental Cloud API) MCP to Claude Code

Create your Vinkius account to connect Vast.ai (GPU Rental Cloud API) 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 Vast.ai (GPU Rental Cloud API) with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search and validate resources using the MCP Server

In a headless environment, you can't click around. You need pure data flow. Use `search_offers` to programmatically check Vast.ai availability, passing structured JSON like `{"gpu_name":{"eq":"RTX 4090"}}`. The output is clean JSON that your script can pipe directly into subsequent commands. This makes the GPU search step a reliable, non-interactive part of any CI/CD job.

Programmatic instance deployment via `rent_instance`

Your shell script needs to provision resources. A call to `rent_instance` executes in the background, starting your GPU container on Vast.ai and returning a usable ID or status code for logging. This is perfect for GitHub Actions that need guaranteed resource setup. You'll write scripts that handle the success codes and failure states of this critical deployment step.

Clean up resources with `delete_instance`

Every script needs a reliable cleanup routine. The `list_instances` tool gives you all active IDs, which your cron job can then loop over calling `delete_instance`. This ensures that if a build fails halfway through, you don't get stuck paying for unused GPU time. The ability to manage the full lifecycle—from list to delete—is critical for SRE work.

Setup guide

Set up Vast.ai (GPU Rental Cloud API) 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 vastai-gpu-rental-cloud-api-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http vastai-gpu-rental-cloud-api-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 Vast.ai (GPU Rental Cloud API) 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": {
    "vastai-gpu-rental-cloud-api-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 Vast.ai. 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 Vast.ai (GPU Rental Cloud API) 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 Vast.ai (GPU Rental Cloud API) MCP in Claude Code

You connect using a single command line invocation. Your script calls the MCP Server, which executes `search_offers` and streams the resulting GPU marketplace data to your terminal or next tool.

This server exposes infrastructure metadata: instance IDs, hardware specifications like specific GPUs, current status, and pricing models for the Vast.ai cloud platform.

Yes. You write a shell script that first executes `search_offers`, captures the output, and then pipes it to a tool that calls `rent_instance`. It's all linear, headless execution.

It does. Since the server only requires an endpoint token and runs via standard transports (like HTTP), it integrates perfectly into Docker containers or GitHub Actions.

Vinkius provides a managed, zero-trust endpoint for these tools. This means your script calls one reliable URL to access multiple functionalities, rather than having to manage different vendor APIs.

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