stop-gpu-instance
Stop a GPU instance on the Novita AI platform to manage resources and control costs. Provide the instance ID to halt compute operations.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| instanceId | Yes | ID of the instance to stop. Before calling the MCP tool to stop the instance, MUST show me the details of the instance to help me identify it, including id, name, etc. |
Implementation Reference
- src/tools.ts:230-242 (handler)Handler function that executes the stop-gpu-instance tool by sending a POST request to the /gpu/instance/stop endpoint with the provided instanceId and returns the JSON response.}, async (params) => { const result = await novitaRequest(`/gpu/instance/stop`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });
- src/tools.ts:227-229 (schema)Zod input schema defining the required instanceId parameter for the stop-gpu-instance tool.instanceId: z .string() .describe("ID of the instance to stop. Before calling the MCP tool to stop the instance, MUST show me the details of the instance to help me identify it, including id, name, etc."),
- src/tools.ts:226-242 (registration)Registration of the stop-gpu-instance tool using server.tool, including schema and inline handler.server.tool("stop-gpu-instance", { instanceId: z .string() .describe("ID of the instance to stop. Before calling the MCP tool to stop 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/stop`, "POST", { instanceId: params.instanceId, }); return { content: [ { type: "text", text: JSON.stringify(result, null, 2), }, ], }; });