CoreWeave (AI GPU Cloud) Connector for AI agents.

24 live capabilities

Provision and manage high-performance GPU clusters and networks.

Live agent request CoreWeave (AI GPU Cloud) / Connector

Waiting for input…

AI Agent

Why people use CoreWeave (AI GPU Cloud)

CoreWeave for GPU Cloud Infrastructure Management

With this Connector, you just ask your agent to check the VPC details. It pulls the info instantly so you can keep your hands on the keyboard and your eyes on the code. You get a direct line to your hardware without the manual overhead.

What Vinkius changes

You get a hands-free way to manage high-performance GPU hardware.

Use it from Claude, ChatGPT, Cursor or another AI client you already have.

One account · 5,900+ Connectors

Real-world use case 01

Scaling training clusters

An ML Engineer needs to spin up 5 more GPU nodes for a large training run.
Real-world use case 02

Network isolation for production

A DevOps lead needs to isolate a production model.
Real-world use case 03

Routing traffic to new models

A researcher wants to route traffic to a new model version.

Complete set · 24capabilities

The complete CoreWeave (AI GPU Cloud) capability set.

These are the exact actions your AI can choose when you ask it to work with CoreWeave (AI GPU Cloud).

Capability set01 / 06

01—04

4 capabilities in this set.

Part of 24 available through CoreWeave (AI GPU Cloud).

01 Capability
Create deployment
Launch a new Inference Deployment for your AI models. This makes your model available for production use.
02 Capability
Create gateway
Set up a new Inference Gateway to manage model traffic. It handles the routing and authentication for your requests.
03 Capability
Delete capacity claim
Remove an Inference Capacity Claim you no longer need. This helps you free up your reserved resources.
04 Capability
Delete deployment
Remove an Inference Deployment from your active list. Use this to clean up old model versions.

Capability set02 / 06

05—08

4 capabilities in this set.

Part of 24 available through CoreWeave (AI GPU Cloud).

05 Capability
Delete gateway
Delete an Inference Gateway that is no longer in use. This simplifies your routing architecture.
06 Capability
Get cluster
Pull the specific details for a CKS cluster. You can use this to check the status of your active compute.
07 Capability
List deployments
Review all your Inference Deployments. Use this to see which models are currently live.
08 Capability
List gateways
Get a list of all your Inference Gateways. This helps you audit your traffic routing.

Capability set03 / 06

09—12

4 capabilities in this set.

Part of 24 available through CoreWeave (AI GPU Cloud).

09 Capability
List vpcs
See all your Virtual Private Clouds at a glance. You can quickly check your network inventory.
10 Capability
Query metrics
Pull Prometheus metrics to see performance data. Use this to monitor your system's health.
11 Capability
Update capacity claim
Change the details of an Inference Capacity Claim. You can adjust your reserved capacity as needs change.
12 Capability
Update cluster
Modify an existing CKS cluster using an update mask. You can change your cluster specs without deleting it.

Capability set04 / 06

13—16

4 capabilities in this set.

Part of 24 available through CoreWeave (AI GPU Cloud).

13 Capability
Update deployment
Adjust an Inference Deployment to change how your model runs. This is useful for swapping out model versions.
14 Capability
Create vpc
Build a new Virtual Private Cloud for your resources. This provides the network isolation your infrastructure needs.
15 Capability
Delete cluster
Tear down a CKS cluster when you're finished with a project. This stops billing for unused bare-metal compute.
16 Capability
Delete vpc
Remove a VPC from your account. This is the final step in decommissioning a network environment.

Capability set05 / 06

17—20

4 capabilities in this set.

Part of 24 available through CoreWeave (AI GPU Cloud).

17 Capability
List capacity claims
View all your Inference Capacity Claims in one list. It's the easiest way to see what's reserved.
18 Capability
List clusters
See every CoreWeave Kubernetes Service (CKS) cluster you have. This gives you a bird's eye view of your hardware.
19 Capability
Query logs
Search through Loki logs to find specific events. This is your go-to for troubleshooting infrastructure issues.
20 Capability
Update gateway
Modify an Inference Gateway to change routing rules. Use this to update how traffic hits your models.

Capability set06 / 06

21—24

4 capabilities in this set.

Part of 24 available through CoreWeave (AI GPU Cloud).

21 Capability
Update vpc
Edit the settings of an existing VPC. You can change CIDR blocks or other network properties here.
22 Capability
Get vpc
See the specific details of a Virtual Private Cloud. This helps you check your network configuration quickly.
23 Capability
Create capacity claim
Request a new Inference Capacity Claim for your models. It ensures you have the resources needed for heavy inference.
24 Capability
Create cluster
Provision a new CoreWeave Kubernetes Service (CKS) cluster. This sets up your bare-metal compute for AI workloads.

Set up in minutes

One URL. Then ask CoreWeave (AI GPU Cloud) to work.

Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use CoreWeave (AI GPU Cloud) from the conversation.

Choose your client

Live preview

Advanced clients IDE · CLI

Claude · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp

Step 01

Open Connectors

In Claude Web or Claude Desktop, open Settings and choose Connectors.
Step 02

Add the URL

Choose Add custom connector, name it CoreWeave (AI GPU Cloud), and paste the URL above.
Step 03

Turn it on in chat

Select +, open Connectors, and enable CoreWeave (AI GPU Cloud) for the conversation.

ChatGPT · Web + desktop

Official guide ↗

Connector URL · ready to paste

Streamable HTTP

https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp

Step 01

Open MCP settings

On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
Step 02

Add the URL

Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the CoreWeave (AI GPU Cloud) URL.
Step 03

Save and start

Save the connection and enable CoreWeave (AI GPU Cloud) in your conversation. Desktop may ask you to restart once.

Cursor · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "coreweave-ai-gpu-cloud": {
      "url": "https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp"
    }
  }
}

Step 01

Open MCP Settings

Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
Step 02

Add the server config

Paste the JSON configuration above into the mcp.json file that opens
Step 03

Save the file

Cursor will automatically detect the new Connector
Step 04

Start using CoreWeave (AI GPU Cloud)

Open Agent mode in chat and ask: "Using CoreWeave (AI GPU Cloud), help me...". 24 tools available

VS Code Copilot · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "coreweave-ai-gpu-cloud": {
      "url": "https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp"
    }
  }
}

Step 01

Create MCP config

Create a .vscode/mcp.json file in your project root
Step 02

Add the server config

Paste the JSON configuration above
Step 03

Enable Agent mode

Open GitHub Copilot Chat and switch to Agent mode using the dropdown
Step 04

Start using CoreWeave (AI GPU Cloud)

Ask Copilot: "Using CoreWeave (AI GPU Cloud), help me...". 24 tools available

Windsurf · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "coreweave-ai-gpu-cloud": {
      "url": "https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp"
    }
  }
}

Step 01

Open MCP Settings

Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
Step 02

Add the server

Paste the JSON configuration above into mcp_config.json
Step 03

Save and reload

Windsurf will detect the new server automatically
Step 04

Start using CoreWeave (AI GPU Cloud)

Open Cascade and ask: "Using CoreWeave (AI GPU Cloud), help me...". 24 tools available

Cline · IDE configuration

Official guide ↗

Advanced setup

{
  "mcpServers": {
    "coreweave-ai-gpu-cloud": {
      "url": "https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp"
    }
  }
}

Step 01

Open Cline MCP Settings

Click the Connectors icon in the Cline sidebar panel
Step 02

Add remote server

Click "Add Connector" and paste the configuration above
Step 03

Enable the server

Toggle the server switch to ON
Step 04

Start using CoreWeave (AI GPU Cloud)

Ask Cline: "Using CoreWeave (AI GPU Cloud), help me...". 24 tools available

Claude Code · Terminal command

Official guide ↗

Advanced setup

claude mcp add coreweave-ai-gpu-cloud --transport http "https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcp"

Step 01

Install Claude Code

Run npm install -g @anthropic-ai/claude-code if not already installed
Step 02

Add the Connector

Run the command above in your terminal
Step 03

Verify the connection

Run claude mcp to list connected servers, or type /mcp inside a session
Step 04

Start using CoreWeave (AI GPU Cloud)

Ask Claude: "Using CoreWeave (AI GPU Cloud), show me...". 24 tools are ready

Where the request belongs

Work CoreWeave can move forward.

Built around the request

This is for the infrastructure engineers and ML researchers who are tired of clicking through cloud consoles at 2am to provision hardware.

01

ML Engineer

Provision and scale GPU clusters for training runs without leaving your dev environment.

02

DevOps Engineer

Automate VPC setup and gateway routing for production-grade AI services.

03

AI Researcher

Quickly inspect cluster status and deployment health during testing phases.

Build the capability set

Each Connector adds new actions and data without changing how you work.

Browse Connectors

01 7 capabilities

Lambda Labs (GPU Cloud)

Manage AI infrastructure via Lambda Labs. launch GPU instances, monitor ML workloads, and manage SSH keys.

02 7 capabilities

RunPod

Integrate your AI securely to RunPod to cleanly quickly provision scalable GPU pods, manage active instances, and inspect serverless endpoints and custom templates natively.

03 4 capabilities

Vast.ai (GPU Rental Cloud API)

Rent high-performance GPUs for AI and deep learning. Search marketplace offers, deploy Docker containers, and manage your cloud GPU fleet.

04 6 capabilities

Paperspace

Provision and track powerful GPU workloads via Paperspace. list compute instances, fetch active deployments, trace team projects, and query Gradient environments via AI.

05 7 capabilities

Modal (Serverless AI Infrastructure)

Manage serverless compute via Modal. audit active apps, track GPU deployments, and monitor network volumes.

06 33 capabilities

Civo (Cloud-native Kubernetes Cloud Provider API)

Manage Civo cloud infrastructure. provision Kubernetes clusters, control compute instances, and monitor usage directly via AI.

Bring your own AI

Change the model, client or framework. Keep CoreWeave connected.

Before you connect

Questions about CoreWeave.

The practical details behind the request, access and result.

Can I use CoreWeave MCP to manage my GPU clusters?

Yes, it lets you provision and manage CKS clusters. You can create new ones for training or tear them down when you're done to save on costs.

Does this Connector support VPC configuration?

Yes, you can create and update VPCs for network isolation. This helps keep your compute resources secure and organized.

Can I use this to monitor my AI models?

Yes, it lets you list deployments and query metrics. You can see which models are live and check their performance in real time.

How do I connect my CoreWeave account?

Just provide your CoreWeave API Token in your client settings. From there, your agent can perform actions on your behalf.

Can I troubleshoot my infrastructure with this?

Yes, you can query Loki logs to find specific events and use Prometheus metrics to see performance data for your clusters.

Is this for production AI workloads?

Yes, it handles gateways and clusters for production-grade inference. It's designed for teams running heavy AI workloads.

Can I delete old clusters to save money?

Yes, you can use the delete_cluster capability to remove clusters you no longer need. This helps you stop billing for unused bare-metal hardware.

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.

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.

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.

One connection away

Give your agent a direct line to CoreWeave.

Connect CoreWeave once. Keep it beside 5,900+ managed Connectors when the next task needs more.

Explore every Connector No credit card required · Free tier available