What models can I access with this MCP?

You can access various hosted configurations, including Nemotron and Llama3 architectures, by using the model listing capability.

Do I need to manage my own NVIDIA SDK?

No. This MCP acts as a proxy that handles the logic and mapping, bypassing the need for manual SDK configuration.

How do I check if I have enough credits for a task?

You can use the token quota capability to poll your current credit status and execution limits.

Can this MCP handle images?

Yes, the vision inference capability allows your agent to perform multimodal tasks on graphical data.

Is this MCP ready to use immediately?

Yes. Vinkius hosts the MCP, so you only need to connect your client once to start using the capabilities.

Can I explicitly route specific embedding vectors natively using the NVIDIA integration matrix?

Yes! Utilize generate_embeddings providing explicit logic extracting arrays natively isolating endpoints safely.

How do I explicitly explore active LLMs natively hosted inside the NVIDIA catalog bounds?

Target explicit matrices natively calling list_foundation_models returning catalog endpoints safely explicitly mapping bounds secure natively.

Does this require local Docker execution mapping explicitly NVIDIA parameters transparently?

No, this explicitly pings the hosted Cloud API. For local Docker metrics natively, switch to nvidia-nim-mcp enforcing natively local boundaries.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect NVIDIA API Catalog to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run high-performance inference directly through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 8 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 8 available through NVIDIA API Catalog.

01
Nvidia list foundation models
Returns a list of all accessible LLM model paths currently hosted in the NVIDIA matrix.
02
Nvidia list lora adapters
Retrieves available fine-tuned LoRA adapters to apply specific logical constraints to models.
03
Nvidia vision inference
Triggers multimodal inference to process and return diagnostic data from graphical inputs.
04
Nvidia chat completion
Executes direct NLP inference queries against hosted large language models.

Capability set02 / 02

05-08

4 capabilities in this set.

Part of 8 available through NVIDIA API Catalog.

05
Nvidia check token quota
Checks your current credit balance and execution limits to prevent inference interruptions.
06
Nvidia generate embeddings
Converts unstructured text into numerical embedding arrays for vector-based tasks.
07
Nvidia get cloud status
Pings NVIDIA's hosted endpoints to check current latency and system availability.
08
Nvidia summarize content
Runs predefined compression logic to condense text into structured summaries.

Real work

What teams actually run

Rapid Model Prototyping

Test different foundation models quickly by querying the available model list.

Vector Database Preparation

Generate embeddings for large datasets to feed into vector search engines.

Automated Content Distillation

Use the summarization capability to process large volumes of text into concise arrays.

Visual Data Analysis

Run vision inference to extract information from images using multimodal models.

Automate a task

Put NVIDIA API Catalog to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

NVIDIA API Catalog works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put NVIDIA API Catalog to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

908ms average. Fast in production.

NVIDIA API Catalog is checked daily against the live service.

Daily averagePeak 1116ms

Oct 3Today

Fastest day: 719ms
Slowest day: 1116ms
14-day trend: Slowing+26%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 8 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of NVIDIA API Catalog, so you can see the experience inside your AI.

It does not authenticate your account with NVIDIA API Catalog. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

NVIDIA API Catalog Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_LgfbZayzkE3ZBfq9HWv3rgeK69AXP0h3anUpakUy/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — NVIDIA API Catalog capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "nvidia-api-catalog-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_LgfbZayzkE3ZBfq9HWv3rgeK69AXP0h3anUpakUy/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up NVIDIA API Catalog in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work NVIDIA API Catalog owners hand off.

This MCP is designed for technical users working directly with large scale generative models.

01
AI Engineers
They use this to bypass manual SDK mapping and run direct inference.
02
Generative Integrators
They connect NVIDIA's compute power to existing application workflows.
03
Developers
They use the capabilities to parse direct responses from public compute matrices.

FAQ

Questions NVIDIA API Catalog owners ask.

01
What models can I access with this MCP?
You can access various hosted configurations, including Nemotron and Llama3 architectures, by using the model listing capability.
02
Do I need to manage my own NVIDIA SDK?
No. This MCP acts as a proxy that handles the logic and mapping, bypassing the need for manual SDK configuration.
03
How do I check if I have enough credits for a task?
You can use the token quota capability to poll your current credit status and execution limits.
04
Can this MCP handle images?
Yes, the vision inference capability allows your agent to perform multimodal tasks on graphical data.
05
Is this MCP ready to use immediately?
Yes. Vinkius hosts the MCP, so you only need to connect your client once to start using the capabilities.
06
Can I explicitly route specific embedding vectors natively using the NVIDIA integration matrix?
Yes! Utilize generate_embeddings providing explicit logic extracting arrays natively isolating endpoints safely.
07
How do I explicitly explore active LLMs natively hosted inside the NVIDIA catalog bounds?
Target explicit matrices natively calling list_foundation_models returning catalog endpoints safely explicitly mapping bounds secure natively.
08
Does this require local Docker execution mapping explicitly NVIDIA parameters transparently?
No, this explicitly pings the hosted Cloud API. For local Docker metrics natively, switch to nvidia-nim-mcp enforcing natively local boundaries.

Explore

More in Industry Titans

Connect NVIDIA API Catalog to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Nvidia list foundation models

Nvidia list lora adapters

Nvidia vision inference

Nvidia chat completion

05-08

Nvidia check token quota

Nvidia generate embeddings

Nvidia get cloud status

Nvidia summarize content

What teams actually run

Rapid Model Prototyping

Vector Database Preparation

Automated Content Distillation

Visual Data Analysis

Building your own app? The connector is yours to use.

NVIDIA API Catalog Connector

Claude Desktop

AI Engineers

Generative Integrators

Developers

What models can I access with this MCP?

Do I need to manage my own NVIDIA SDK?

How do I check if I have enough credits for a task?

Can this MCP handle images?

Is this MCP ready to use immediately?

Can I explicitly route specific embedding vectors natively using the NVIDIA integration matrix?

How do I explicitly explore active LLMs natively hosted inside the NVIDIA catalog bounds?

Does this require local Docker execution mapping explicitly NVIDIA parameters transparently?

LiteLLM (LLM Proxy & Spend Tracking) AI Connector

Modelbit (ML Model Deployments) AI Connector

DeepInfra (Serverless LLM Inference) AI Connector

AI Foundation Model Valuation Engine AI Connector

Suggestions

Model Routing Efficiency Calculator AI Connector

AI Model Selection ROI Engine AI Connector

NVIDIA AI AI Connector

Model Routing Optimizer AI Connector