$ loading_
Let AI manage cloud clusters, jobs, and storage with SkyPilot.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "skypilot-mcp" yet — see the docs or source repo.
Using SkyPilot, create a cloud cluster for model training with 4 GPUs, automatically choose the most cost-effective cloud region, and return the cluster name, config summary, and estimated cost.
Returns the created or planned cluster details, including resources, region choice, and cost estimate.
Submit this data preprocessing script as a batch job to an existing SkyPilot cluster, set it to automatically retry twice on failure, and tell me the job ID, status, and how to view logs.
Returns the job submission result, job identifier, current status, and log and retry configuration details.
Using SkyPilot, check the status of the project storage bucket; if it does not exist, create a new one, upload the training data to the specified path, and summarize the storage location and access method.
Returns the bucket check or creation result, upload status, destination path, and follow-up access instructions.
Query multiple Kubernetes clusters at once using natural language.
Connect to the mcp API via MCP to extend AI tool capabilities.
Manage Kubernetes resources with natural language for deployment and troubleshooting.
Manage Kubernetes clusters, resources, backups, and diagnostics using natural language.
Manage and route multiple MCP servers from one cloud dashboard.
Parse multi-cloud IaC and generate real-time cost estimates and comparisons.