Skip to main content
Glama
novitalabs

Novita MCP Server

Official
by novitalabs

get-template

Retrieve a specific template by ID from the Novita MCP Server to manage AI platform resources efficiently. Simplifies template access for GPU instance operations.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
templateIdYesID of the template to retrieve

Implementation Reference

  • src/tools.ts:328-347 (registration)
    Registration of the 'get-template' tool, including input schema (templateId: string) and inline async handler that constructs a query for the templateId and fetches details from the Novita API endpoint '/template' using the novitaRequest helper, returning formatted JSON text content.
    server.tool("get-template", { templateId: z .string() .describe("ID of the template to retrieve"), }, async (params) => { const queryParams = new URLSearchParams(); queryParams.append("templateId", params.templateId); const queryString = queryParams.toString() ? `?${queryParams.toString()}` : ""; const result = await novitaRequest(`/template${queryString}`); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });
  • Input schema for the 'get-template' tool defining the required 'templateId' parameter as a string with description.
    templateId: z .string() .describe("ID of the template to retrieve"),
  • Handler function for 'get-template' that queries the Novita API with the provided templateId and returns the result as a text content block with JSON stringified.
    }, async (params) => { const queryParams = new URLSearchParams(); queryParams.append("templateId", params.templateId); const queryString = queryParams.toString() ? `?${queryParams.toString()}` : ""; const result = await novitaRequest(`/template${queryString}`); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });
  • Supporting utility function novitaRequest used by the get-template handler to perform authenticated HTTP requests to the Novita AI API.
    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