start-gpu-instance
Initiate GPU instance operations by specifying the instance ID to start using the Novita MCP Server. Ideal for managing AI platform resources efficiently.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| instanceId | Yes | ID of the instance to start |
Implementation Reference
- src/tools.ts:212-224 (handler)The async handler function that sends a POST request to the Novita API endpoint `/gpu/instance/start` with the instanceId to start the GPU instance and returns the formatted result.}, async (params) => { const result = await novitaRequest(`/gpu/instance/start`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });
- src/tools.ts:209-211 (schema)Zod schema defining the input parameter `instanceId` as a required string with description.instanceId: z .string() .describe("ID of the instance to start"),
- src/tools.ts:208-224 (registration)The server.tool call that registers the "start-gpu-instance" tool, including its input schema and inline handler function.server.tool("start-gpu-instance", { instanceId: z .string() .describe("ID of the instance to start"), }, async (params) => { const result = await novitaRequest(`/gpu/instance/start`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });