An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Coreweave AI GPU Cloud to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage high-performance AI infrastructure through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 24 capabilities

We ship only the actions that matter.

Capability set01 / 06

01-04

4 capabilities in this set.

Part of 24 available through CoreWeave.

  1. 01

    Query logs

    Retrieves logs from Loki for debugging.

  2. 02

    Update capacity claim

    Updates the details of an existing Capacity Claim.

  3. 03

    Update cluster

    Modifies a CKS cluster using an update mask.

  4. 04

    Create cluster

    Provisions a new CKS cluster.

Capability set02 / 06

05-08

4 capabilities in this set.

Part of 24 available through CoreWeave.

  1. 05

    Create vpc

    Sets up a new Virtual Private Cloud.

  2. 06

    Delete capacity claim

    Removes an existing Inference Capacity Claim from your account.

  3. 07

    Delete cluster

    Deletes a CKS cluster from your infrastructure.

  4. 08

    Delete gateway

    Removes an Inference Gateway.

Capability set03 / 06

09-12

4 capabilities in this set.

Part of 24 available through CoreWeave.

  1. 09

    Delete vpc

    Removes a Virtual Private Cloud.

  2. 10

    Get cluster

    Retrieves detailed information for a specific CKS cluster.

  3. 11

    List capacity claims

    Lists all active and past Inference Capacity Claims.

  4. 12

    List clusters

    Provides a list of all CoreWeave Kubernetes Service (CKS) clusters.

Capability set04 / 06

13-16

4 capabilities in this set.

Part of 24 available through CoreWeave.

  1. 13

    List deployments

    Returns a list of all your current Inference Deployments.

  2. 14

    List gateways

    Shows all configured Inference Gateways.

  3. 15

    List vpcs

    Returns a list of all your Virtual Private Clouds.

  4. 16

    Query metrics

    Fetches data from Prometheus metrics for monitoring.

Capability set05 / 06

17-20

4 capabilities in this set.

Part of 24 available through CoreWeave.

  1. 17

    Update deployment

    Modifies the configuration of an existing Inference Deployment.

  2. 18

    Update gateway

    Changes the configuration of an Inference Gateway.

  3. 19

    Update vpc

    Changes the settings of an existing VPC.

  4. 20

    Create capacity claim

    Generates a new Inference Capacity Claim.

Capability set06 / 06

21-24

4 capabilities in this set.

Part of 24 available through CoreWeave.

  1. 21

    Create deployment

    Sets up a new Inference Deployment.

  2. 22

    Create gateway

    Provisions a new Inference Gateway.

  3. 23

    Delete deployment

    Deletes a specific Inference Deployment.

  4. 24

    Get vpc

    Fetches specific details for a single VPC.

Real work

What teams actually run

01

Rapid Cluster Scaling

Scale up your CKS clusters immediately when a new training job requires more GPU capacity.

02

Automated Model Deployment

Deploy new model versions and configure gateways to route traffic to them via a single prompt.

03

Real-time Debugging

Ask your agent to pull Loki logs or Prometheus metrics when a deployment shows errors.

04

Network Isolation

Quickly create and update VPCs to ensure your sensitive workloads stay on isolated networks.

Automate a task

Put CoreWeave to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

CoreWeave works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put CoreWeave to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1008ms average. Fast in production.

CoreWeave is checked daily against the live service.

Daily averagePeak 1112ms
Oct 3Today
Fastest day
774ms
Slowest day
1112ms
14-day trend
Improving-6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 24 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of CoreWeave, so you can see the experience inside your AI.

It does not authenticate your account with CoreWeave. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

CoreWeave Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — CoreWeave capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "coreweave-ai-gpu-cloud-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up CoreWeave in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work CoreWeave owners hand off.

This MCP is built for technical teams managing large-scale AI workloads on specialized hardware.

  • 01

    ML Engineers

    They use the agent to provision and scale GPU clusters without leaving their dev environment.

  • 02

    DevOps Teams

    They automate VPC setup and gateway routing for production AI services.

  • 03

    AI Researchers

    They check cluster status and deployment health during training or testing.

FAQ

Questions CoreWeave owners ask.

  • 01

    How do I connect this MCP to my AI client?

    You subscribe to the MCP on Vinkius and enter your CoreWeave API Token. Once connected, you can use it immediately in any MCP-compatible client like Claude or Cursor.

  • 02

    Which AI clients are compatible with this MCP?

    This MCP works with any client that supports the Model Context Protocol, including Claude, Cursor, and Windsurf.

  • 03

    Do I need to manage the hosting for this MCP?

    No, Vinkius hosts and manages the MCP for you, so it is ready to use as soon as you connect your credentials.

  • 04

    Can I use this for monitoring my deployments?

    Yes, the MCP includes capabilities to query Prometheus metrics and Loki logs so your agent can inspect deployment health.

  • 05

    What kind of infrastructure can I manage?

    You can manage CKS clusters, VPCs, Inference Deployments, Capacity Claims, and Inference Gateways.

  • 06

    Can I list all my active Kubernetes clusters across the CoreWeave infrastructure?

    Yes. By using the list_clusters capability, your agent will retrieve a complete list of all bare-metal Kubernetes clusters (CKS) managed under your account.

  • 07

    How do I check the specific network configuration of a VPC?

    You can use the get_vpc capability by providing the specific VPC ID. The agent will return detailed information about network isolation and configuration for that resource.

  • 08

    Is it possible to create a new inference gateway via the AI agent?

    Absolutely. Use the create_gateway capability with the required specification JSON. This allows you to set up routing and authentication for your AI model traffic programmatically.

Explore

More in Cloud Infrastructure

Suggestions

Connect CoreWeave to Claude, Cursor, ChatGPT & more