Which AI models are available?

The NVIDIA API Catalog offers Llama 3.1 (8B, 70B, 405B), Mistral, CodeLlama, Gemma, Nemotron, and many more. Use the `list_models` tool to see all available models.

How do I get an NVIDIA API Key?

Sign up at [**build.nvidia.com**](https://build.nvidia.com), go to your account settings, and generate an API key. The Developer Program includes free inference credits.

Can I generate code in specific languages?

Yes! The `generate_code` tool lets you specify the programming language (Python, JavaScript, TypeScript, Java, etc.) for better results.

Are there usage limits on the free tier?

Yes, the NVIDIA Developer Program provides free inference credits. Once exhausted, you can upgrade to a paid plan for higher throughput. Check your usage dashboard at build.nvidia.com.

NVIDIA AI MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: NVIDIA AI
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect NVIDIA AI through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to NVIDIA AI "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in NVIDIA AI?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About NVIDIA AI MCP Server

Connect NVIDIA AI to any AI agent and harness the power of GPU-accelerated foundation models — chat with Llama, generate embeddings, write code with CodeLlama, translate text, and perform complex reasoning through the NVIDIA API Catalog.

Pydantic AI validates every NVIDIA AI tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Chat with LLMs — Access Llama 3.1, Mistral, Nemotron, and more via chat completions
Generate Embeddings — Create vector embeddings for search and clustering
Code Generation — Write code from natural language prompts using CodeLlama
Summarization — Condense long documents into concise summaries
Translation — Neural translation between dozens of languages
Text-to-SQL — Convert natural language questions into SQL queries
Sentiment Analysis — Analyze the emotional tone of text
Complex Reasoning — Ask questions to the 405B-parameter reasoning model

The NVIDIA AI MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect NVIDIA AI to Pydantic AI via MCP

Follow these steps to integrate the NVIDIA AI MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from NVIDIA AI with type-safe schemas

Why Use Pydantic AI with the NVIDIA AI MCP Server

Pydantic AI provides unique advantages when paired with NVIDIA AI through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your NVIDIA AI integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your NVIDIA AI connection logic from agent behavior for testable, maintainable code

NVIDIA AI + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the NVIDIA AI MCP Server delivers measurable value.

Type-safe data pipelines: query NVIDIA AI with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple NVIDIA AI tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query NVIDIA AI and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock NVIDIA AI responses and write comprehensive agent tests

NVIDIA AI MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect NVIDIA AI to Pydantic AI via MCP:

analyze_sentiment

Analyze the sentiment of a text

ask_question

Optionally provide context for better answers. Ask a question to a powerful reasoning model (405B params)

chat_completion

Use "model" to specify which AI model (e.g., "meta/llama-3.1-70b-instruct", "mistralai/mistral-large"). Messages should be in OpenAI format: [{role: "user", content: "..."}]. Chat with an NVIDIA AI model (Llama, Mistral, etc)

generate_code

Specify language if needed. Generate code from a natural language prompt

get_embeddings

Model: "nvidia/nv-embed-v1". Generate vector embeddings from text

list_models

List all available AI models on the NVIDIA API Catalog

summarize_text

Summarize long text into a concise version

text_to_sql

Convert natural language to SQL query

translate_text

Translate text to another language

Example Prompts for NVIDIA AI in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with NVIDIA AI immediately.

"Generate Python code for a REST API with FastAPI."

"Translate 'Hello, how are you?' to Japanese."

"Summarize: The quarterly report shows revenue grew 15% YoY..."

Troubleshooting NVIDIA AI MCP Server with Pydantic AI

Common issues when connecting NVIDIA AI to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

NVIDIA AI + Pydantic AI FAQ

Common questions about integrating NVIDIA AI MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your NVIDIA AI MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.