How to Use the NVIDIA API Catalog MCP in Pydantic AI

Q: How do I initialize the NVIDIA API Catalog MCP Server in Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp" and instantiate MCPToolset with your Vinkius HTTP URL. Pass this toolset directly to your Agent constructor inside the toolsets parameter.

Q: How does Pydantic AI handle schema errors from the NVIDIA API Catalog?

If nvidiachatcompletion returns a payload that violates your Pydantic model, the framework raises a validation error instantly. This prevents the agent from hallucinating fields or passing broken data to your database.

Q: How do I discover available models and adapters?

Your agent can call nvidialistfoundationmodels to get a structured list of active endpoints. It can also query nvidialistloraadapters to find active fine-tuning configurations.

Run type-safe NVIDIA API Catalog operations with Pydantic AI to validate every model response at runtime.

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 Pydantic AI

Create your Vinkius account to connect NVIDIA API Catalog to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe inference for Pydantic AI

Stop dealing with silent schema corruption in production. This MCP Server integrates with Pydantic AI to validate responses from `nvidia_chat_completion` against your strict Python models at runtime. If the model returns malformed data, your agent catches the validation error immediately instead of passing corrupted fields downstream. This ensures absolute reliability for critical business logic.

Validate embeddings and token limits at runtime

Keep your vector databases clean and your budgets under control. Your agent calls `nvidia_generate_embeddings` and validates the output dimensions before inserting them into your index. Before firing off expensive requests, the agent checks `nvidia_check_token_quota` to verify credit limits. Pydantic AI enforces these constraints, failing loudly if you are about to exceed your limits.

Type-safe vision and content summaries

Parse images and documents with strict schema enforcement. The agent calls `nvidia_vision_inference` to analyze graphics, mapping the output directly into a validated Python class. For long texts, `nvidia_summarize_content` compresses the data while preserving the structured fields your application expects. You can also monitor endpoint health with `nvidia_get_cloud_status` to ensure high availability across your MCP pipeline.

Setup guide

Set up NVIDIA API Catalog MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "nvidia-api-catalog-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to NVIDIA API Catalog tools.",
)

result = await agent.run("List recent NVIDIA API Catalog transactions")
print(result.output)

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 Pydantic AI

Install the slim package with `pip install "pydantic-ai-slim[mcp]"` and instantiate `MCPToolset` with your Vinkius HTTP URL. Pass this toolset directly to your `Agent` constructor inside the `toolsets` parameter.

If `nvidia_chat_completion` returns a payload that violates your Pydantic model, the framework raises a validation error instantly. This prevents the agent from hallucinating fields or passing broken data to your database.

Yes, the framework supports both Streamable HTTP and SSE transports. Use the unified `MCPToolset` class to connect to your externally running Vinkius proxy endpoint.

Your agent can call `nvidia_list_foundation_models` to get a structured list of active endpoints. It can also query `nvidia_list_lora_adapters` to find active fine-tuning configurations.

No, your schemas, chat history, and token usage metrics are never persisted. The proxy runs in an ephemeral, zero-trust V8 sandbox that processes payloads on the fly and wipes the session state the moment the request completes.

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