restart-gpu-instance
Restart a GPU instance on the Novita AI platform to resolve issues or apply configuration changes by specifying the instance ID.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| instanceId | Yes | ID of the instance to restart. Before calling the MCP tool to restart the instance, MUST show me the details of the instance to help me identify it, including id, name, etc. |
Implementation Reference
- src/tools.ts:266-278 (handler)The handler function that executes the tool logic: makes a POST request to the Novita API endpoint `/gpu/instance/restart` with the provided instanceId and returns the result as formatted JSON text content.}, async (params) => { const result = await novitaRequest(`/gpu/instance/restart`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });
- src/tools.ts:263-265 (schema)Zod schema for the tool's input parameters, specifically validating the instanceId as a string with a descriptive note.instanceId: z .string() .describe("ID of the instance to restart. Before calling the MCP tool to restart the instance, MUST show me the details of the instance to help me identify it, including id, name, etc."),
- src/tools.ts:262-278 (registration)The server.tool call that registers the 'restart-gpu-instance' tool, including its schema and inline handler function.server.tool("restart-gpu-instance", { instanceId: z .string() .describe("ID of the instance to restart. Before calling the MCP tool to restart the instance, MUST show me the details of the instance to help me identify it, including id, name, etc."), }, async (params) => { const result = await novitaRequest(`/gpu/instance/restart`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });