How to Use the NVIDIA API Catalog MCP in Mastra AI

Q: Does Mastra AI support NVIDIA API Catalog tool approval?

You can force human-in-the-loop verification by setting requireToolApproval on the server tools. This is ideal for sensitive operations like modifying production data or spending tokens.

Q: Can I use NVIDIA API Catalog for embeddings in Mastra AI?

Yes. Use nvidiagenerateembeddings to turn unstructured data into vectors. These vectors are then easily stored in your vector database for agent retrieval tasks.

Q: How do I verify connection health for my Mastra AI agents?

Periodically call nvidiagetcloudstatus in a background heartbeat task. If the latency exceeds your threshold, you can fail over to a local model or alert your team.

Build resilient multi-step workflows in Mastra AI using hardened NVIDIA API Catalog foundation models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA API Catalog MCP to Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated workflow branching

Integrate complex logic into your agents by routing tasks based on model output. You use `nvidia_chat_completion` as a decision node within your Mastra AI engine. If the initial model response misses a requirement, your workflow can trigger a retry or pivot to a different path automatically. This reduces the need for manual intervention in your business logic.

Manage model adapters dynamically

Swap fine-tuned logic on the fly to suit different agent personas. You invoke `nvidia_list_lora_adapters` to check which overrides are available for your current task. This lets your agents specialize without loading massive static models. It keeps your memory footprint small while maintaining high output quality for specific domain queries.

Summarize data between agent steps

Compress lengthy agent logs or research results into tight summaries before passing them to the next node. You trigger `nvidia_summarize_content` to keep your context window clean. This prevents your agents from getting overwhelmed by long strings of text. It saves tokens and improves the accuracy of downstream autonomous decisions.

Setup guide

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

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

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

Use the built-in retry mechanisms in your agent workflow. If `nvidia_get_cloud_status` returns an error, your agent can catch the exception and wait for the endpoint to recover.

You can force human-in-the-loop verification by setting `requireToolApproval` on the server tools. This is ideal for sensitive operations like modifying production data or spending tokens.

Yes. Use `nvidia_generate_embeddings` to turn unstructured data into vectors. These vectors are then easily stored in your vector database for agent retrieval tasks.

Periodically call `nvidia_get_cloud_status` in a background heartbeat task. If the latency exceeds your threshold, you can fail over to a local model or alert your team.

Absolutely. You can define a sequence where the output of one tool feeds the input of another. Mastra AI handles the state management between these steps.

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