How to Use the NVIDIA NIM MCP in Mastra AI

Q: How does Mastra AI interact with NVIDIA NIM logs?

You can add nimgetcontainerlogs to your agent tools. This allows the agent to inspect stdout proxies whenever an inference task hits an error.

Q: Can I use Mastra AI to query NVIDIA NIM metrics?

Yes, nimgetmetrics provides the Prometheus data you need. Your agent can read these values to decide if the system needs more replicas.

Q: How do I list models via Mastra AI on NVIDIA NIM?

Add nimlistmodels to your agent's toolset. It will return the full list of active LLMs that your agent can target for specific tasks.

Build complex inference workflows with Mastra AI by automating GPU scaling and health checks via an MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA NIM MCP to Mastra AI

Create your Vinkius account to connect NVIDIA NIM to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup NVIDIA NIM with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate health checks in workflows

Integrate `nim_check_health_live` into your Mastra agent logic to verify container responsiveness before proceeding with inference tasks. If the probe fails, your workflow can trigger a retry or alert an admin. This creates a self-healing loop for your infrastructure. You aren't just running agents; you're building systems that verify their own environment before executing code.

Orchestrate inference scaling

Use `nim_scale_replicas` as a step in your agent-driven workflows to adjust hardware usage based on demand. You can set conditional branches that scale down when usage drops to save costs. This gives your agents control over the physical backend. You define the logic, and the server executes the scaling commands immediately.

Get deep model metadata

Run `nim_get_metadata` to map your foundational configuration bounds into your workflow state. This allows your agents to make informed decisions about which models to use based on current loaded limits. Your code gets a clear view of exactly what the NVIDIA NIM server is running. It removes the guesswork from model selection and resource allocation.

Setup guide

Set up NVIDIA NIM MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All NVIDIA NIM tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "nvidia-nim-mcp-client",
  servers: {
    "nvidia-nim-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "NVIDIA NIM Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to NVIDIA NIM tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent NVIDIA NIM transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by NVIDIA NIM. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect NVIDIA NIM now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about NVIDIA NIM MCP in Mastra AI

You can add `nim_get_container_logs` to your agent tools. This allows the agent to inspect stdout proxies whenever an inference task hits an error.

Yes, `nim_get_metrics` provides the Prometheus data you need. Your agent can read these values to decide if the system needs more replicas.

Since Mastra handles retries natively, any tool call failure from `nim_check_health_ready` will trigger your configured exponential backoff automatically.

Add `nim_list_models` to your agent's toolset. It will return the full list of active LLMs that your agent can target for specific tasks.

Your container logs are accessed locally through the MCP protocol. No metrics or logs are transmitted to third-party services; they stay within your managed environment for maximum security.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript