Skip to main content
Glama
novitalabs

Novita MCP Server

Official
by novitalabs

start-gpu-instance

Start a GPU instance on the Novita AI platform to activate computing resources for AI workloads. Provide the instance ID to initiate operation.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
instanceIdYesID of the instance to start

Implementation Reference

  • The handler function that performs the core logic: sends a POST request to the Novita API endpoint `/gpu/instance/start` with the instance ID and returns the formatted JSON response as tool output.
    }, async (params) => { const result = await novitaRequest(`/gpu/instance/start`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });
  • Zod input schema defining the required `instanceId` parameter as a string.
    instanceId: z .string() .describe("ID of the instance to start"),
  • src/tools.ts:208-224 (registration)
    Registers the "start-gpu-instance" tool on the MCP server with its 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), }, ], }; });
  • Supporting utility function that handles authenticated HTTP requests to the Novita AI API, used by the tool handler to start the GPU instance.
    export async function novitaRequest( endpoint: string, method: string = "GET", body: any = null ) { // Base URL for Novita AI API const API_BASE_URL = "https://api.novita.ai/gpu-instance/openapi/v1"; // Get API key from environment variable const API_KEY = process.env.NOVITA_API_KEY; const url = `${API_BASE_URL}${endpoint}`; const headers = { Authorization: `Bearer ${API_KEY}`, "Content-Type": "application/json", }; const options: any = { method, headers, }; if (body && (method === "POST" || method === "PATCH")) { options.body = JSON.stringify(body); } try { const response = await fetch(url, options); if (!response.ok) { const errorText = await response.text(); throw new Error(`Novita AI API Error: ${response.status} - ${errorText}`); } // Some endpoints might not return JSON const contentType = response.headers.get("content-type"); if (contentType && contentType.includes("application/json")) { return await response.json(); } return { success: true, status: response.status }; } catch (error) { console.error("Error calling Novita AI API:", error); throw error; } }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/novitalabs/novita-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server