How to Use the NVIDIA NIM MCP in VS Code Copilot

Q: Can VS Code Copilot check if my NVIDIA NIM model is ready?

Yes. Copilot calls nimcheckhealthready to verify that the inference layers have successfully loaded the model artifacts, preventing premature API requests.

Manage, monitor, and scale NVIDIA NIM containers across your entire team using 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 NIM MCP to VS Code Copilot

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track container health inside VS Code Copilot

Monitor container states across your team using `nim_check_health_live` to verify host runner status. By checking in a shared configuration for this MCP Server, everyone gets instant access to liveness probes directly in the chat panel. Copilot uses `nim_check_health_ready` to ensure model weights are fully loaded. This stops developers from running tests against uninitialized containers, saving hours of debugging time.

Read GPU metrics with this MCP Server

Track physical VRAM limits using `nim_get_gpu_status` to stop guessing if your dev server is overloaded. This MCP Server lets Copilot run topological checks to pull physical hardware variables into your shared workspace. With `nim_get_metrics` and `nim_get_metadata`, your agent extracts live Prometheus performance data. It gives your team the exact numbers they need to optimize local inference code.

Manage model deployment and active replicas

Inspect the list of active LLMs using `nim_list_models` to see what is loaded on your logical backend. Control your local deployment setup without leaving your editor by querying active inference targets instantly. When load testing, the agent can call `nim_scale_replicas` to adjust replication layers dynamically. This lets you simulate production scaling events right from your chat panel.

Setup guide

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

.vscode/mcp.json

{
  "mcpServers": {
    "nvidia-nim-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 NIM. 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 NIM 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 NIM MCP in VS Code Copilot

Create a configuration file in your workspace root directory and commit it to your Git repository. Every developer with the extension installed will instantly get access to the tools.

Yes. Copilot calls `nim_check_health_ready` to verify that the inference layers have successfully loaded the model artifacts, preventing premature API requests.

You can ask Copilot to analyze your hardware. The agent runs `nim_get_gpu_status` and `nim_get_metrics` to display live VRAM usage and Prometheus scaling data.

You must have access to the container host running your containers. The server queries the local container socket or API to fetch metrics and manage replicas.

The server operates entirely within your local security boundaries. It parses container logs and model metadata locally, ensuring that raw operational metrics are never exposed to external cloud environments.

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