Novita MCP Server

by novitalabs
MIT License
70
2

create-gpu-instance

Deploy GPU instances on Novita MCP Server by specifying name, product ID, GPU count, root filesystem size, and Docker image URL. Configure ports, environment variables, and network storage mounts to customize the instance for AI and compute workloads.

Input Schema

NameRequiredDescriptionDefault
commandNoContainer start command to run when the instance starts
envNoEnvironment variables
gpuNumYesNumber of GPUs allocated to the instance. The availableGpuNumber of the product must be greater than or equal to the gpuNum.
imageAuthIdNoID of the container registry auth. Required only when the imageUrl is private. You can use the `list-container-registry-auths` tool to check the ID if you're not sure.
imageUrlYesDocker image URL to initialize the instance
kindNoType of the instancegpu
nameYesName for the instance. Must contain only numbers, letters, and hyphens
networkStoragesNoNetwork storages to mount
portsNoPorts to expose (e.g., '8888/http', '22/tcp'), separated by commas if multiple. Maximum of 10 ports.
productIdYesID of the product used to deploy the instance. The availableGpuNumber of the product must be greater than 0. You can use the `list-products` tool to get or check the product ID if needed. Before calling the MCP tool, MUST show me the details of the product to help me identify it, including name, price, etc.
rootfsSizeYesRoot filesystem size (container disk size) in GB. Free tier includes 60GB.

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "command": { "description": "Container start command to run when the instance starts", "maxLength": 2048, "type": "string" }, "env": { "description": "Environment variables", "items": { "additionalProperties": false, "properties": { "key": { "description": "Environment variable key", "maxLength": 2048, "minLength": 1, "type": "string" }, "value": { "description": "Environment variable value", "maxLength": 2048, "type": "string" } }, "required": [ "key", "value" ], "type": "object" }, "type": "array" }, "gpuNum": { "description": "Number of GPUs allocated to the instance. The availableGpuNumber of the product must be greater than or equal to the gpuNum.", "minimum": 1, "type": "number" }, "imageAuthId": { "description": "ID of the container registry auth. Required only when the imageUrl is private. You can use the `list-container-registry-auths` tool to check the ID if you're not sure.", "type": "string" }, "imageUrl": { "description": "Docker image URL to initialize the instance", "maxLength": 500, "minLength": 1, "type": "string" }, "kind": { "default": "gpu", "description": "Type of the instance", "enum": [ "gpu" ], "type": "string" }, "name": { "description": "Name for the instance. Must contain only numbers, letters, and hyphens", "maxLength": 255, "type": "string" }, "networkStorages": { "description": "Network storages to mount", "items": { "additionalProperties": false, "properties": { "Id": { "description": "ID of the network storage to mount. You can use the `list-network-storage` tool to get or check the ID if needed. The network storage's cluster must match the product's cluster.", "minLength": 1, "type": "string" }, "mountPoint": { "description": "Path to mount the network storage", "minLength": 1, "type": "string" } }, "required": [ "Id", "mountPoint" ], "type": "object" }, "type": "array" }, "ports": { "description": "Ports to expose (e.g., '8888/http', '22/tcp'), separated by commas if multiple. Maximum of 10 ports.", "type": "string" }, "productId": { "description": "ID of the product used to deploy the instance. The availableGpuNumber of the product must be greater than 0. You can use the `list-products` tool to get or check the product ID if needed. Before calling the MCP tool, MUST show me the details of the product to help me identify it, including name, price, etc.", "minLength": 1, "type": "string" }, "rootfsSize": { "description": "Root filesystem size (container disk size) in GB. Free tier includes 60GB.", "minimum": 10, "type": "number" } }, "required": [ "name", "productId", "gpuNum", "rootfsSize", "imageUrl" ], "type": "object" }
ID: f1rv6j126v