NVIDIA Vision Connector for AI agents.
9 live capabilities
Generate images and analyze visual data with production-grade computer vision.
Waiting for input…
Why people use NVIDIA Vision
NVIDIA Vision for Computer Vision
This Connector puts all those capabilities into your agent's hands. You can just point your agent at a pile of documents or a folder of photos and tell it to extract the data, describe the scenes, or generate new assets in one go. You get a finished result instead of a dozen half-finished tasks.
What Vinkius changes
You get production-grade computer vision and image generation without managing any infrastructure.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Rapid mood board generation
A designer needs a mood board.
- Real-world use case 02
Automated receipt processing
A clerk handles invoices.
- Real-world use case 03
Retail inventory scanning
A developer builds a retail app.
Complete set · 9capabilities
The complete NVIDIA Vision capability set.
These are the exact actions your AI can choose when you ask it to work with NVIDIA Vision.
01—03
3 capabilities in this set.
Part of 9 available through NVIDIA Vision.
- 01 Capability
Image captioning
Generate a detailed text description of what is happening in a provided image. Use this to create alt-text or summaries for visual content.
- 02 Capability
Detect objects
List every recognizable object found in an image for data analysis. This gives your agent a structured list of everything in a photo.
- 03 Capability
Document qa
Ask questions about scanned documents, forms, or receipts to extract specific text. This is perfect for automating data entry from physical files.
04—06
3 capabilities in this set.
Part of 9 available through NVIDIA Vision.
- 04 Capability
Generate image
Create high-quality images from text prompts using Stable Diffusion 3 or XL models. You can specify sizes and styles to get the exact look you want.
- 05 Capability
Visual grounding
Locate a specific object or phrase within an image to get its exact position. This helps your agent interact with specific parts of a photo.
- 06 Capability
Image segmentation
Identify and separate all distinct objects in an image into their own regions. This is useful for complex scene analysis and item counting.
07—09
3 capabilities in this set.
Part of 9 available through NVIDIA Vision.
- 07 Capability
Style transfer
Apply a specific artistic style to an existing image to change its look and feel. Use this to maintain brand consistency across different assets.
- 08 Capability
List vision models
Check which vision models are currently available on the NVIDIA API Catalog. This helps you see what capabilities are currently accessible.
- 09 Capability
Visual question answering
Provide an image URL and ask your agent specific questions about its content. This allows for deep interaction with visual data.
Set up in minutes
One URL. Then ask NVIDIA Vision to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use NVIDIA Vision from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it NVIDIA Vision, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable NVIDIA Vision for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the NVIDIA Vision URL.
- Step 03
Save and start
Save the connection and enable NVIDIA Vision in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-vision": {
"url": "https://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using NVIDIA Vision
Open Agent mode in chat and ask: "Using NVIDIA Vision, help me...". 9 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-vision": {
"url": "https://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using NVIDIA Vision
Ask Copilot: "Using NVIDIA Vision, help me...". 9 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-vision": {
"url": "https://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using NVIDIA Vision
Open Cascade and ask: "Using NVIDIA Vision, help me...". 9 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"nvidia-vision": {
"url": "https://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using NVIDIA Vision
Ask Cline: "Using NVIDIA Vision, help me...". 9 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add nvidia-vision --transport http "https://edge.vinkius.com/vk_preview_sRxLMKjkyXafjuH9XFRfp9b6jC4r9s5alORDsgz8/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using NVIDIA Vision
Ask Claude: "Using NVIDIA Vision, show me...". 9 tools are ready
Where the request belongs
Work NVIDIA can move forward.
Designers who need to prototype visuals fast, developers who want to add vision features without building a backend, and content creators who need to scale image production.
Creative Director
Creates mood boards and style guides by generating various visual concepts from text prompts.
Backend Developer
Integrates document OCR and object detection into apps without spinning up GPU clusters.
Social Media Manager
Turns blog posts into captioned images and styled visuals quickly to maintain brand consistency.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsHugging Face Vision
Connect Hugging Face Vision to any AI agent via MCP.
SigmaMind AI
Train custom computer vision models with your own images and deploy object detection and classification without ML expertise.
EyePop.ai
Add computer vision to your apps with pre-trained models for object detection, face recognition, and image classification.
Roboflow
Manage computer vision workflows. upload images, train models, and manage datasets directly from your AI agent.
Clarifai (Vision AI)
Manage AI inference via Clarifai. list apps, models, and workflows, and perform computer vision predictions directly from any AI agent.
Luma AI (Generative Video & Creative)
Generate cinematic AI videos and images via Luma. use Dream Machine for text-to-video, image-to-video, and professional camera control.
Bring your own AI
Change the model, client or framework. Keep NVIDIA connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about NVIDIA.
The practical details behind the request, access and result.
Can I use NVIDIA Vision MCP to generate images?
Yes, it uses Stable Diffusion models to create high-quality images from your text descriptions.
Does NVIDIA Vision MCP work with scanned documents?
Yes, it includes capabilities to read and understand scanned documents, forms, and receipts.
How do I get images from my agent using NVIDIA Vision?
Once connected, you simply ask your agent to create an image. It will use the Connector to generate the file for you.
Can I use this for object detection?
Yes, it can identify and list every recognizable object found in a photo to help you analyze scenes.
Is there a way to change the style of a photo?
Yes, you can use style transfer to apply specific artistic styles to existing images.
Can it read my receipts?
Yes, it handles receipts and other forms, allowing your agent to extract specific data points automatically.
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').
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.
Does it work with scanned documents?
Yes! Use document_qa to extract information from scanned documents, forms, receipts, and other image-based documents.
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.
One connection away
Give your agent a direct line to NVIDIA.
Connect NVIDIA once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available