Skip to main content
Glama
runpod

RunPod MCP Server

Official
by runpod

start-pod

Start a RunPod compute pod by providing its ID to resume execution of AI workloads and applications.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
podIdYesID of the pod to start

Implementation Reference

  • The handler function that executes the 'start-pod' tool. It calls the RunPod API to start the pod with the given podId and returns the JSON response as text content.
    async (params) => {
      const result = await runpodRequest(`/pods/${params.podId}/start`, 'POST');
    
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(result, null, 2),
          },
        ],
      };
    }
  • Zod input schema defining the required 'podId' parameter for the 'start-pod' tool.
    {
      podId: z.string().describe('ID of the pod to start'),
    },
  • src/index.ts:258-275 (registration)
    Registration of the 'start-pod' tool using server.tool(), specifying the name, input schema, and handler function.
    server.tool(
      'start-pod',
      {
        podId: z.string().describe('ID of the pod to start'),
      },
      async (params) => {
        const result = await runpodRequest(`/pods/${params.podId}/start`, 'POST');
    
        return {
          content: [
            {
              type: 'text',
              text: JSON.stringify(result, null, 2),
            },
          ],
        };
      }
    );
  • Shared utility function 'runpodRequest' that makes authenticated HTTP requests to the RunPod API, used by the 'start-pod' 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'

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