Use CoreWeave with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Manage high-performance AI infrastructure on CoreWeave. provision GPU clusters, configure VPCs, and orchestrate inference gateways directly from your AI agent.
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.
Complete set · 24 capabilities
The complete CoreWeave capability set.
These are the exact actions your AI can choose when you ask it to work with CoreWeave.
01-04
4 capabilities in this set.
Part of 24 available through CoreWeave.
- 01
Delete capacity claim
Delete an Inference Capacity Claim
- 02
Delete deployment
Delete an Inference Deployment
- 03
Delete gateway
Delete an Inference Gateway
- 04
Get cluster
Get details for a specific CKS cluster
05-08
4 capabilities in this set.
Part of 24 available through CoreWeave.
- 05
List deployments
List all Inference Deployments
- 06
List gateways
List all Inference Gateways
- 07
Query metrics
Query Prometheus metrics
- 08
Update deployment
Update an Inference Deployment
09-12
4 capabilities in this set.
Part of 24 available through CoreWeave.
- 09
Delete cluster
Delete a CKS cluster
- 10
Delete vpc
Delete a VPC
- 11
List capacity claims
List all Inference Capacity Claims
- 12
List clusters
List all CoreWeave Kubernetes Service (CKS) clusters
13-16
4 capabilities in this set.
Part of 24 available through CoreWeave.
- 13
Query logs
Query Loki logs
- 14
Update vpc
Update a VPC
- 15
Create capacity claim
Create a new Inference Capacity Claim
- 16
Create deployment
Create a new Inference Deployment
17-20
4 capabilities in this set.
Part of 24 available through CoreWeave.
- 17
Create gateway
Create a new Inference Gateway
- 18
Create vpc
Create a new VPC
- 19
List vpcs
List all Virtual Private Clouds (VPCs)
- 20
Update capacity claim
Update an Inference Capacity Claim
21-24
4 capabilities in this set.
Part of 24 available through CoreWeave.
- 21
Update cluster
Requires an updateMask in the payload. Update a CKS cluster
- 22
Update gateway
Update an Inference Gateway
- 23
Get vpc
Get details for a specific VPC
- 24
Create cluster
Create a new CKS cluster
Observed, not estimated
942ms average. Fast in production.
CoreWeave is checked daily against the live service.
- Fastest day
- 778ms
- Slowest day
- 1163ms
- 14-day trend
- Slowing+15%
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.
https://edge.vinkius.com/vk_preview_a151JnxoNH7y2muaVwaqzr9Q5YKz8wmiZJSE1HZv/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — CoreWeave capabilities are ready to use.
{
"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
FAQ
Questions CoreWeave owners ask.
- 01
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.
- 02
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.
- 03
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
TrueFoundry AI Connector
Universal LLM Gateway & ML deployment hub: invoke 1000+ proxy models and manage MCP service instances natively
ViewLambda Labs (GPU Cloud) AI Connector
Manage AI infrastructure via Lambda Labs — launch GPU instances, monitor ML workloads, and manage SSH keys.
ViewReplicate AI Connector
Equip your AI to dynamically search, run, and monitor thousands of open-source machine learning models hosted
ViewDatadog AI (LLM Observability) AI Connector
Monitor LLM performance via Datadog — track token usage, audit prompts, and monitor AI model metrics directly
View
Suggestions
Gridscale (IaaS & PaaS Cloud Hosting API) AI Connector
Manage your Gridscale cloud infrastructure — provision servers, monitor metrics, and control PaaS services dir
ViewBraintrust AI Connector
Automate AI evaluations with Braintrust — organize projects, test model datasets, run benchmarks, and manage p
ViewHaystack (deepset Cloud) AI Connector
Build and manage AI-powered search and RAG pipelines via deepset Cloud — search documents, run pipelines, and
ViewCerebras Inference AI Connector
Access lightning-fast AI inference via Cerebras Wafer-Scale Engine — generate chat completions, manage models,
View
