How to Use the NVIDIA AI MCP in VS Code Copilot

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

Create a .vscode/mcp.json file in your repository root and add the server details. When your team members open the project in VS Code 1.96 or higher, Copilot Chat will automatically load the tools.

Q: Can VS Code Copilot use NVIDIA AI to generate code snippets?

Yes, the generatecode tool allows Copilot to write code based on your open files. The tool returns clean, structured code blocks that fit right into your active workspace.

Equip your entire engineering team with NVIDIA AI tools inside VS Code Copilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA AI MCP to VS Code Copilot

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Share SQL tools across VS Code Copilot teams

The `text_to_sql` tool lets VS Code Copilot translate plain English instructions into database queries for your whole team. Onboarding developers to a complex database schema takes weeks. By committing the MCP Server configuration to your repository, every engineer gets access to this tool instantly. It reduces the time spent on manual SQL writing and helps prevent syntax errors in your team's pull requests.

Analyze text sentiment in your workspace

The `analyze_sentiment` tool lets VS Code Copilot scan text files and customer feedback directly inside your workspace. Processing user feedback files shouldn't require spinning up a separate data science pipeline. This lets your team build and test data pipelines locally. The server handles the API routing, giving your team instant sentiment analysis without leaving their active workspace.

Ask complex questions to heavy models

The `ask_question` tool connects VS Code Copilot to NVIDIA's 405B parameter reasoning model for complex architectural decisions. When your team faces a tough architectural bottleneck, standard models often fall short. This gives your engineers high-tier reasoning capabilities right inside their chat sidebar. It helps resolve complex debugging scenarios faster by providing deep technical explanations directly in VS Code.

Setup guide

Set up NVIDIA AI 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 AI 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 AI tools listed. Try asking: "List my recent NVIDIA AI transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "nvidia-ai-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 AI 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 AI MCP in VS Code Copilot

Create a `.vscode/mcp.json` file in your repository root and add the server details. When your team members open the project in VS Code 1.96 or higher, Copilot Chat will automatically load the tools.

Yes, the `generate_code` tool allows Copilot to write code based on your open files. The tool returns clean, structured code blocks that fit right into your active workspace.

Vinkius handles the API authentication centrally. Your team only needs a single endpoint token configured in the workspace settings, removing the need to distribute raw NVIDIA API keys to every developer.

Yes, you can pass long log files or system dumps to Copilot Chat and use the `summarize_text` tool. It will generate a concise breakdown of the errors, helping your team debug issues faster.

Your SQL schemas and metadata are sent over TLS to the NVIDIA API Catalog only to generate the requested queries. The Vinkius MCP Server operates in a secure, isolated sandbox, meaning your database structures are never stored or used for model training.

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