How to Use the NVIDIA API Catalog MCP in OpenAI Agents SDK

Q: How do I configure the NVIDIA API Catalog MCP Server with OpenAI Agents SDK?

Install the package with pip install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass the server instance inside the mcpservers list when instantiating your Agent. Set cacheToolsList=True to speed up tool discovery during agent execution.

Q: How do I trace NVIDIA API Catalog calls inside the OpenAI Agents SDK dashboard?

Every tool execution, from nvidiagenerateembeddings to nvidiavisioninference, automatically emits telemetry to your dashboard. This makes debugging your MCP integrations straightforward.

Q: Can my agent switch between different foundation models dynamically?

Yes, your agent can call nvidialistfoundationmodels to check active paths and swap them. It can also query nvidialistloraadapters to locate fine-tuned overrides for specific tasks.

Q: How is my prompt data secured when using this MCP Server?

Your model prompts and raw image bytes sent to nvidiavisioninference bypass local storage entirely. Vinkius runs this server in an isolated, zero-trust V8 sandbox, routing your payloads securely to NVIDIA's API endpoints and destroying the connection state immediately after execution.

Run Nemotron and Llama3 models in your OpenAI Agents SDK pipelines with native guardrails and zero-config tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect NVIDIA API Catalog to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure model discovery for OpenAI Agents SDK

Let your agent map out active endpoints instantly. This MCP Server integration registers `nvidia_list_foundation_models` directly into your agent constructor, letting the SDK auto-discover available model paths without manual mapping. Once registered, your agent runs queries using `nvidia_chat_completion` while honoring your built-in OpenAI safety guardrails. You get clean, validated responses routed directly through your dashboard.

Track quotas and latency inside the SDK

Stop guessing why an agent run failed in production. Your agent can call `nvidia_check_token_quota` to verify credit limits before executing massive batch tasks, saving you from abrupt rate-limit crashes. To keep agent handoffs fast, use `nvidia_get_cloud_status` to evaluate the latency of the cloud endpoints. If an endpoint lags, the agent can hand off the task to a different specialized loop.

Run vision and embeddings across agent nodes

Feed image data directly to your multi-agent workflows. The agent calls `nvidia_vision_inference` to extract metadata from graphical files, passing the structured output to downstream text agents. For retrieval tasks, the SDK calls `nvidia_generate_embeddings` to vectorize inputs on the fly. You can also run `nvidia_summarize_content` to compress long documents across your MCP client boundaries.

Setup guide

Set up NVIDIA API Catalog MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all NVIDIA API Catalog tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives NVIDIA API Catalog tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate NVIDIA API Catalog tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="NVIDIA API Catalog Agent",
            instructions="You have access to NVIDIA API Catalog tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package with `pip install openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass the server instance inside the `mcp_servers` list when instantiating your Agent. Set `cacheToolsList=True` to speed up tool discovery during agent execution.

Yes, the SDK validates all tool calls before execution. When your agent invokes `nvidia_chat_completion`, the SDK checks your configured policies to block unauthorized queries before they hit the cloud proxy.

Every tool execution, from `nvidia_generate_embeddings` to `nvidia_vision_inference`, automatically emits telemetry to your dashboard. This makes debugging your MCP integrations straightforward.

Yes, your agent can call `nvidia_list_foundation_models` to check active paths and swap them. It can also query `nvidia_list_lora_adapters` to locate fine-tuned overrides for specific tasks.

Your model prompts and raw image bytes sent to `nvidia_vision_inference` bypass local storage entirely. Vinkius runs this server in an isolated, zero-trust V8 sandbox, routing your payloads securely to NVIDIA's API endpoints and destroying the connection state immediately after execution.

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