How to Use the CoreWeave (AI GPU Cloud) MCP in Claude

Q: How do I connect CoreWeave (AI GPU Cloud) to Claude Desktop?

Open your claudedesktopconfig.json file and add the server config under the mcpServers key. Restart the desktop app, and you will see the tools ready to use via the hammer icon in your chat window.

Q: Can I manage my VPCs using CoreWeave (AI GPU Cloud) inside Claude Desktop?

Yes, you can. Your agent uses createvpc and listvpcs to configure isolated networking zones directly within your conversation.

Q: Does the CoreWeave (AI GPU Cloud) MCP Server support capacity reservations in Claude Desktop?

Absolutely. You can use createcapacityclaim and updatecapacityclaim to reserve high-end NVIDIA GPUs before you kick off massive training runs.

Deploy and scale GPU workloads directly from Claude Desktop with zero context switching.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CoreWeave (AI GPU Cloud) MCP to Claude Desktop

Create your Vinkius account to connect CoreWeave (AI GPU Cloud) to Claude Desktop 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 CoreWeave (AI GPU Cloud) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run GPU Clusters on CoreWeave

`create_cluster` spins up a new CoreWeave Kubernetes Service (CKS) cluster right from your chat prompt. You can check the status using `get_cluster` or pull down the entire list of environments with `list_clusters` to verify your setup is active. Instead of clicking through a web console, you tell your agent to provision the nodes. This MCP Server handles the Kubernetes API calls behind the scenes so you focus on your model training code.

Manage Inference Deployments in Claude Desktop

`create_deployment` launches your model inference endpoints directly onto CoreWeave's bare-metal GPU infrastructure. Your agent uses `update_deployment` to adjust scale, while `delete_deployment` tears down idle resources to stop billing. Route traffic instantly by pairing these deployments with `create_gateway` to handle external requests. This setup means your AI client manages the entire lifecycle of your production models without you running manual terminal scripts.

Debug with Real-Time Loki and Prometheus Logs

`query_logs` pulls Loki logs from your active containers directly into your chat window. When a container crashes, your agent runs `query_metrics` to grab Prometheus metrics and diagnose why the GPU ran out of memory. Having these diagnostics in your sidebar speeds up troubleshooting. You don't need to open Grafana or run kubectl commands to find out why a deployment failed.

Setup guide

Set up CoreWeave (AI GPU Cloud) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The CoreWeave (AI GPU Cloud) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the CoreWeave (AI GPU Cloud) MCP configuration

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

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under coreweave-ai-gpu-cloud-mcp.

json

{
  "mcpServers": {
    "coreweave-ai-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 CoreWeave. 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 CoreWeave (AI 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 CoreWeave (AI GPU Cloud) MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the server config under the `mcpServers` key. Restart the desktop app, and you will see the tools ready to use via the hammer icon in your chat window.

Yes, you can. Your agent uses `create_vpc` and `list_vpcs` to configure isolated networking zones directly within your conversation.

Absolutely. You can use `create_capacity_claim` and `update_capacity_claim` to reserve high-end NVIDIA GPUs before you kick off massive training runs.

No, you do not need kubectl or helm. The server communicates directly with the cloud APIs, letting your agent handle cluster management on your behalf.

Your API tokens, Loki logs, and Prometheus metrics never pass through third-party servers. All interactions run locally on your machine via stdio, ensuring your infrastructure credentials and system performance data remain entirely inside your secure network.

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