How to Use the CoreWeave (AI GPU Cloud) MCP in VS Code Copilot

Q: How does our team share the CoreWeave (AI GPU Cloud) config in VS Code Copilot?

You create a .vscode/mcp.json file in your repository root. Once committed, any team member with the Copilot extension gets immediate access to the MCP Server tools.

Q: Can VS Code Copilot scale our CoreWeave (AI GPU Cloud) deployments?

Yes. Copilot uses updatedeployment and updatecapacityclaim to scale your GPU resources up or down based on your workload demands.

Q: How do we verify our CoreWeave (AI GPU Cloud) clusters in VS Code Copilot?

You run listclusters and getcluster via the Copilot chat. The agent returns the current state of your Kubernetes nodes directly in the sidebar.

Manage bare-metal GPU resources with VS Code Copilot across your entire development team.

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 VS Code Copilot

Create your Vinkius account to connect CoreWeave (AI 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 CoreWeave (AI GPU Cloud) with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-Wide VPC Control in VS Code Copilot

`create_vpc` builds secure network boundaries for your team's machine learning models. Every developer can run `list_vpcs` and `get_vpc` to ensure their local testing environments match the remote staging subnets. Committing this MCP Server configuration to your repository means your entire team gets identical access. No one has to manually share network IDs or copy-paste security group rules.

Monitor GPU Environments Directly

`query_metrics` fetches real-time Prometheus statistics from your active training runs. When training speeds drop, `query_logs` pulls Loki logs to let your team debug performance bottlenecks together. Copilot reads this data to suggest optimizations. You get direct advice on batch sizes or memory limits based on actual cluster performance.

Deploy Inference Gateways in Copilot

`create_gateway` establishes the routing path for your newly deployed machine learning models. Your team can run `list_gateways` to audit active endpoints and use `delete_gateway` to clean up old routes. This ensures your staging environments stay clean. Your developers can manage the lifecycle of public endpoints without requesting admin access to a cloud dashboard.

Setup guide

Set up CoreWeave (AI 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 CoreWeave (AI 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 CoreWeave (AI GPU Cloud) tools listed. Try asking: "List my recent CoreWeave (AI GPU Cloud) transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

You create a `.vscode/mcp.json` file in your repository root. Once committed, any team member with the Copilot extension gets immediate access to the MCP Server tools.

Yes. Copilot uses `update_deployment` and `update_capacity_claim` to scale your GPU resources up or down based on your workload demands.

You run `list_clusters` and `get_cluster` via the Copilot chat. The agent returns the current state of your Kubernetes nodes directly in the sidebar.

You need VS Code version 1.96 or higher to support custom tool integrations.

All API requests to manage your deployments and clusters are sent directly to the cloud endpoint. Your configuration details and private endpoint URLs are never processed by external intermediaries, adhering to strict enterprise-grade MCP Server setups.

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