Skip to main content
Glama

create-network-volume

Create persistent storage volumes for RunPod cloud GPU instances to store data across pod sessions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName for the network volume
sizeYesSize in GB (1-4000)
dataCenterIdYesData center ID

Implementation Reference

  • Handler function that POSTs to RunPod /networkvolumes API with input params and formats response as MCP content.
    async (params) => { const result = await runpodRequest('/networkvolumes', 'POST', params); return { content: [ { type: 'text', text: JSON.stringify(result, null, 2), }, ], }; }
  • Input schema using Zod for name (string), size (number in GB), dataCenterId (string).
    { name: z.string().describe('Name for the network volume'), size: z.number().describe('Size in GB (1-4000)'), dataCenterId: z.string().describe('Data center ID'), },
  • src/index.ts:666-685 (registration)
    MCP server tool registration including name, input schema, and handler function.
    server.tool( 'create-network-volume', { name: z.string().describe('Name for the network volume'), size: z.number().describe('Size in GB (1-4000)'), dataCenterId: z.string().describe('Data center ID'), }, async (params) => { const result = await runpodRequest('/networkvolumes', 'POST', params); return { content: [ { type: 'text', text: JSON.stringify(result, null, 2), }, ], }; } );
  • Shared helper for making authenticated HTTP requests to RunPod API endpoints, used by the tool handler.
    async function runpodRequest( endpoint: string, method: string = 'GET', body?: Record<string, unknown> ) { const url = `${API_BASE_URL}${endpoint}`; const headers = { Authorization: `Bearer ${API_KEY}`, 'Content-Type': 'application/json', }; const options: NodeFetchRequestInit = { 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(`RunPod 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 RunPod 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/runpod/runpod-mcp-ts'

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