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

Q: How do I configure CoreWeave (AI GPU Cloud) in Cursor?

Add the server settings to your .cursor/mcp.json file. Once saved, enable Agent mode in the chat panel to let your editor call the infrastructure tools.

Q: Can I deploy models to CoreWeave (AI GPU Cloud) using Cursor Agent?

Yes, you can. The agent invokes createdeployment and creategateway to push your local model code to live cloud GPUs.

Q: How does Cursor use CoreWeave (AI GPU Cloud) to manage clusters?

Your editor uses listclusters and updatecluster to modify your Kubernetes setups. The agent can adjust your node pools based on the project you are working on.

Write infrastructure code and spin up CoreWeave GPUs inside Cursor with real-time agent execution.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate and Test VPC Networks

`create_vpc` sets up isolated networking for your GPU workloads directly from your code editor. Your agent uses `get_vpc` to fetch subnet details and injects those exact parameters straight into your configuration files. This MCP Server eliminates the guesswork of writing YAML manifests. You get working networking code that matches your live infrastructure because the agent reads the actual cloud state.

Claim GPU Capacity from Cursor

`create_capacity_claim` reserves specific GPU resources like H100s or A100s directly while you write your training script. If your requirements change, `update_capacity_claim` modifies your reservation, and `list_capacity_claims` shows your active allocations. Doing this inside your editor means you can match your resource requests to your code. Your agent checks available hardware and updates the claim without you switching to a web browser.

Debug Deployments with Cursor MCP Server

`query_logs` retrieves live container stdout directly into your editor's terminal pane. When an inference script throws an error, `query_metrics` pulls memory and compute data so your agent can rewrite the broken code on the spot. This loop keeps you in flow. You fix bugs instantly because the agent analyzes actual runtime metrics alongside your source files.

Setup guide

Set up CoreWeave (AI 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 CoreWeave (AI 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 CoreWeave (AI GPU Cloud) transactions." If the MCP tools are loaded correctly, Cursor will call the CoreWeave (AI GPU Cloud) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Add the server settings to your `.cursor/mcp.json` file. Once saved, enable Agent mode in the chat panel to let your editor call the infrastructure tools.

Yes, you can. The agent invokes `create_deployment` and `create_gateway` to push your local model code to live cloud GPUs.

Your editor uses `list_clusters` and `update_cluster` to modify your Kubernetes setups. The agent can adjust your node pools based on the project you are working on.

Yes. You can configure complex cluster setups and claim multi-node GPU groups using the cluster and capacity claim tools.

Your cloud credentials and live container logs are stored locally in your editor's configuration. The MCP Server executes commands using local processes, meaning no external party ever intercepts your infrastructure access keys or system logs.

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