Skip to main content
Glama
novitalabs

Novita MCP Server

Official
by novitalabs

list-gpu-instances

List and filter GPU instances on the Novita AI platform to manage resources by name, product, or status.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageSizeNoNumber of instances to return,
pageNumberNoPage number to return, start from
nameNoFilter by the instance name
productNameNoFilter by the product name
statusNoFilter by the instance status

Implementation Reference

  • Handler function that constructs URL query parameters from input params, makes API request to /gpu/instances endpoint using novitaRequest helper, clears sensitive information, and returns the result as JSON-formatted text content.
        if (params.pageSize)
            queryParams.append("pageSize", params.pageSize.toString());
        if (params.pageNumber)
            queryParams.append("pageNumber", params.pageNumber.toString());
        if (params.name)
            queryParams.append("name", params.name);
        if (params.productName)
            queryParams.append("productName", params.productName);
        if (params.status)
            queryParams.append("status", params.status);
        const queryString = queryParams.toString()
            ? `?${queryParams.toString()}`
            : "";
        const result = await novitaRequest(`/gpu/instances${queryString}`);
        clearSensitiveInfo(result);
    
        return {
            content: [
                {
                    type: "text",
                    text: JSON.stringify(result, null, 2),
                },
            ],
        };
    });
  • Zod-based input schema defining optional parameters for pagination (pageSize, pageNumber), filtering by name, productName, and status.
        pageSize: z
            .number()
            .min(0)
            .default(10)
            .optional()
            .describe("Number of instances to return, "),
        pageNumber: z
            .number()
            .min(0)
            .default(1)
            .optional()
            .describe("Page number to return, start from "),
        name: z
            .string()
            .max(1024)
            .optional()
            .describe("Filter by the instance name"),
        productName: z
            .string()
            .optional()
            .describe("Filter by the product name"),
        status: z
            .enum(["running", "pulling", "exited", "resetting", "removed", "migrating", "freezing"])
            .optional()
            .describe("Filter by the instance status"),
    }, async (params) => {
        // Construct query parameters
        const queryParams = new URLSearchParams();
  • src/tools.ts:62-115 (registration)
    Direct registration of the 'list-gpu-instances' tool on the MCP server within registerGPUInstanceTools function.
    server.tool("list-gpu-instances", {
        pageSize: z
            .number()
            .min(0)
            .default(10)
            .optional()
            .describe("Number of instances to return, "),
        pageNumber: z
            .number()
            .min(0)
            .default(1)
            .optional()
            .describe("Page number to return, start from "),
        name: z
            .string()
            .max(1024)
            .optional()
            .describe("Filter by the instance name"),
        productName: z
            .string()
            .optional()
            .describe("Filter by the product name"),
        status: z
            .enum(["running", "pulling", "exited", "resetting", "removed", "migrating", "freezing"])
            .optional()
            .describe("Filter by the instance status"),
    }, async (params) => {
        // Construct query parameters
        const queryParams = new URLSearchParams();
        if (params.pageSize)
            queryParams.append("pageSize", params.pageSize.toString());
        if (params.pageNumber)
            queryParams.append("pageNumber", params.pageNumber.toString());
        if (params.name)
            queryParams.append("name", params.name);
        if (params.productName)
            queryParams.append("productName", params.productName);
        if (params.status)
            queryParams.append("status", params.status);
        const queryString = queryParams.toString()
            ? `?${queryParams.toString()}`
            : "";
        const result = await novitaRequest(`/gpu/instances${queryString}`);
        clearSensitiveInfo(result);
    
        return {
            content: [
                {
                    type: "text",
                    text: JSON.stringify(result, null, 2),
                },
            ],
        };
    });
  • novitaRequest helper: Performs authenticated HTTP requests to the Novita AI GPU instance API, used by the tool handler to fetch the list of GPU instances.
    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;
        }
    }
  • clearSensitiveInfo helper: Removes sensitive fields like sshPassword from the API response data before returning it.
    export function clearSensitiveInfo(data: any) {
        if (data && data.instances) {
            data.instances = data.instances.map((instance: any) => ({
                ...instance,
                sshPassword: undefined
            }));
        }
    }
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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