CoreWeave (AI GPU Cloud) MCP Connector for Claude
A+Manage high-performance AI infrastructure on CoreWeave — provision GPU clusters, configure VPCs, and orchestrate inference gateways directly from your AI agent.
Connect your CoreWeave account to any AI agent to manage specialized GPU cloud infrastructure through natural language conversation.
What you can do
- Kubernetes Clusters (CKS) — List, create, and manage bare-metal Kubernetes clusters optimized for intensive AI and ML workloads.
- Network Isolation (VPC) — Configure Virtual Private Clouds to ensure secure, isolated networking for your compute resources.
- Inference Gateways — Orchestrate gateways for routing and authenticating traffic to your deployed AI models.
- Deployment Monitoring — List and inspect inference deployments to ensure your services are running at peak performance.
- Resource Lifecycle — Full CRUD operations for clusters, VPCs, and gateways to automate your infrastructure scaling.
How it works
- Subscribe to this server
- Enter your CoreWeave API Token
- Start managing your GPU cloud from Claude, Cursor, or any MCP-compatible client
Who is this for?
- ML Engineers — Provision and scale GPU clusters without leaving your development environment.
- DevOps Teams — Automate VPC setup and gateway routing for production-grade AI services.
- AI Researchers — Quickly inspect cluster status and deployment health during model training or testing phases.
Related Connectors
Predibase (LLM Serving & Finetuning) MCP
Deploy and query fine-tuned LLMs via Predibase — run inference, classify text, and monitor deployment metrics directly from your AI agent.
Gridscale (IaaS & PaaS Cloud Hosting API) MCP
Manage your Gridscale cloud infrastructure — provision servers, monitor metrics, and control PaaS services directly from any AI agent.
Clarifai (Vision AI) MCP
Manage AI inference via Clarifai — list apps, models, and workflows, and perform computer vision predictions directly from any AI agent.
Cerebras Inference MCP
Access lightning-fast AI inference via Cerebras Wafer-Scale Engine — generate chat completions, manage models, and run batch jobs at record speeds.