An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Nvidia Vision 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. Turn text into images and images into actionable data.

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

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.

A futuristic MCP client docking bay
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 · 9 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through NVIDIA.

  1. 01

    Image captioning

    This capability generates a detailed text caption for any image you provide.

  2. 02

    Detect objects

    Use this to identify and list every object visible within an image.

  3. 03

    Document qa

    This capability lets you ask specific questions about scanned documents, forms, or receipts using OCR and visual understanding.

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through NVIDIA.

  1. 04

    Generate image

    This capability creates new images from your text prompts using Stable Diffusion models.

  2. 05

    Image segmentation

    This capability segments an image to identify and isolate distinct object regions.

  3. 06

    List vision models

    This capability retrieves a list of all available vision models in the NVIDIA API Catalog.

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through NVIDIA.

  1. 07

    Style transfer

    Use this to apply specific artistic styles to an existing image.

  2. 08

    Visual grounding

    This capability locates specific objects or phrases within a given image.

  3. 09

    Visual question answering

    This capability allows you to ask questions about an image via a public URL.

Real work

What teams actually run

01

Automated Document Processing

Your agent can extract key figures from a batch of scanned receipts or invoices.

02

Rapid Prototyping

Designers can generate visual ideas for projects using text prompts.

03

Visual Content Auditing

An agent can scan images to detect specific objects or verify content.

04

Creative Asset Editing

You can change the look of an image by applying different artistic styles.

Automate a task

Put NVIDIA 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 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.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

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

You don't need a client to put NVIDIA 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

969ms average. Fast in production.

NVIDIA is checked daily against the live service.

Daily averagePeak 1152ms
Oct 5Today
Fastest day
739ms
Slowest day
1152ms
14-day trend
Slowing+23%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 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, so you can see the experience inside your AI.

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

NVIDIA Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — NVIDIA capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "nvidia-vision-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/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 in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work NVIDIA owners hand off.

This MCP is built for professionals who need to bridge the gap between text-based AI and visual media.

  • 01

    Designers

    They use the capability to generate rapid visual concepts and analyze compositions.

  • 02

    Developers

    They integrate vision capabilities into applications without managing GPU hardware.

  • 03

    Content Creators

    They generate social media assets and apply style transfers to existing content.

FAQ

Questions NVIDIA owners ask.

  • 01

    What AI clients can I use with this MCP?

    You can use this MCP with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 02

    Do I need my own GPU to run this?

    No. Vinkius hosts the MCP, and it uses NVIDIA's cloud-based APIs, so you don't need to manage any local hardware.

  • 03

    Where do I get an NVIDIA API key?

    You can obtain your key at build.nvidia.com.

  • 04

    Can I generate images with specific sizes?

    Yes, the generate_image capability supports specific size formats like 1024x1024.

  • 05

    How does the document understanding work?

    The document_qa capability uses OCR and visual understanding to answer questions about scanned images of forms or receipts.

  • 06

    Can I generate images from text?

    Yes! Use the generate_image capability with Stable Diffusion models. Provide a descriptive prompt and optionally specify size (e.g., '1024x1024').

  • 07

    Can I ask questions about an image?

    Yes! Use visual_question_answering with a public image URL and your question. The AI will analyze and respond with details about the image.

  • 08

    Does it work with scanned documents?

    Yes! Use document_qa to extract information from scanned documents, forms, receipts, and other image-based documents.

  • 09

    What image sizes can I generate?

    Stable Diffusion models support various sizes including 512x512, 768x768, and 1024x1024. Higher resolutions produce more detailed images but take longer to generate.

Explore

More in Industry Titans

Suggestions

Connect NVIDIA to Claude, Cursor, ChatGPT & more