How to Use the NVIDIA Vision MCP in VS Code Copilot

Q: How do we share the NVIDIA Vision MCP configuration in VS Code Copilot?

Create a .vscode/mcp.json file in your repository's root directory. Once committed, any team member opening the project in VS Code 1.96 or higher will automatically load the vision tools.

Q: What tools can we use for artistic rendering?

The styletransfer tool lets you apply artistic styles to images. You can also use imagecaptioning to generate detailed descriptions of the resulting files for documentation purposes.

Q: Is our scanned receipt data secure when using these tools?

Yes. All data sent to documentqa or detectobjects is processed in a secure V8 Isolate sandbox managed by Vinkius. The sandbox is completely ephemeral, ensuring that sensitive financial or personal information is never logged, written to persistent storage, or exposed to external networks.

Share NVIDIA Vision capabilities across your entire engineering team in VS Code Copilot with zero manual setup.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA Vision MCP to VS Code Copilot

Create your Vinkius account to connect NVIDIA Vision to VS Code Copilot 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 Vision with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-wide image analysis in VS Code Copilot

The `detect_objects` tool scans any image to locate and list all present objects. By committing `.vscode/mcp.json` to your repository, your entire team gets immediate access to this MCP Server inside VS Code Copilot. Developers can analyze asset directories or verify UI elements without installing local Python dependencies or machine learning libraries. Everyone uses the exact same managed API configuration.

Automated document parsing for enterprise apps

The `document_qa` tool extracts structured information and answers questions about scanned documents, forms, and receipts. In VS Code Copilot, your team can ask questions about scanned invoices directly within the code editor. The agent uses the tool responses to write schema validation code and mock data structures. This accelerates the development of document processing pipelines for enterprise clients.

Verify visual models with this MCP Server

The `list_vision_models` tool retrieves the active catalog of vision models directly from the NVIDIA API. VS Code Copilot queries this list to ensure your application code references valid, production-ready endpoints. It prevents runtime errors caused by deprecated model names. Your team always works with the latest available visual models, verified directly within the workspace.

Setup guide

Set up NVIDIA Vision MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the NVIDIA Vision MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the NVIDIA Vision tools listed. Try asking: "List my recent NVIDIA Vision transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "nvidia-vision-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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. 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 Vision 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 Vision MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository's root directory. Once committed, any team member opening the project in VS Code 1.96 or higher will automatically load the vision tools.

Yes. By using the image generation tool, VS Code Copilot can produce 1024x1024 visual assets from text prompts inside your chat, saving them directly to your project directory.

Vinkius handles the authentication centrally. Your team uses a single endpoint token configured in the shared JSON file, eliminating the need to distribute individual API keys to every developer.

The `style_transfer` tool lets you apply artistic styles to images. You can also use `image_captioning` to generate detailed descriptions of the resulting files for documentation purposes.

Yes. All data sent to `document_qa` or `detect_objects` is processed in a secure V8 Isolate sandbox managed by Vinkius. The sandbox is completely ephemeral, ensuring that sensitive financial or personal information is never logged, written to persistent storage, or exposed to external networks.

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