How to Use the NVIDIA AI MCP in Mastra AI

Build resilient multi-step workflows with NVIDIA AI and Mastra AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA AI MCP to Mastra AI

Create your Vinkius account to connect NVIDIA AI 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 AI with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Complex logic flows with Mastra AI

Chain `text_to_sql` and `chat_completion` inside your Mastra workflows to automate data retrieval. If a query fails, you can define branch logic to retry or alert your team. This MCP Server provides the building blocks for agents that handle high-stakes tasks. Your workflow engine manages the state while the tools handle the specialized reasoning.

Autonomous task handling in Mastra AI

Use `ask_question` to let your agents reason through ambiguous inputs before executing a task. You can gate these actions with human-in-the-loop approvals to ensure accuracy. The integration enables your agents to perform multi-step operations like summarizing documents and then translating the result. It is built for reliability in production environments.

Structured data processing for Mastra AI

Extract vector embeddings using `get_embeddings` to feed your agent's memory banks. This allows your Mastra agents to maintain context across long-running operations. Connect the tools to your Mastra workflow triggers to process incoming data streams. The MCP Server ensures that your agents always have the latest model capabilities from the NVIDIA API Catalog.

Setup guide

Set up NVIDIA AI 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 AI 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-ai-mcp-client",
  servers: {
    "nvidia-ai-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent NVIDIA AI 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. 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 AI 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 AI MCP in Mastra AI

Import the MCP client into your agent definition file. Use the spread operator to inject the tool definitions directly into the agent's tool array.

Yes. Mastra supports built-in exponential backoff. Configure your workflow steps to catch API errors and trigger a retry cycle automatically.

It is. Enable the approval requirement in your agent configuration. Your agents will pause until a human confirms the tool execution.

Mastra persists the execution state in your database. When an agent calls an MCP tool, the result is logged, allowing for perfect audit trails.

Data is transmitted directly to the NVIDIA API Catalog via encrypted channels. No PII or proprietary data is cached on our servers; the MCP bridge serves only as a conduit for your request payloads.

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