How to Use the NVIDIA NIM MCP in Claude

Q: How does Claude Desktop handle NVIDIA NIM health checks?

The agent runs nimcheckhealthlive to verify the container host is responsive. It then uses nimcheckhealthready to ensure the specific GPU inference layers have successfully loaded your model weights.

Control local GPU inference containers and scale replicas directly inside Claude Desktop.

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 Claude Desktop

Create your Vinkius account to connect NVIDIA NIM to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track container health inside Claude Desktop

Verify host states immediately using `nim_check_health_live` to see if your local containers are actually running. This MCP Server lets your agent run liveness probes natively to confirm the runner is responsive, followed by `nim_check_health_ready` to ensure the model weights are fully loaded. When things go sideways, you don't need to jump to a terminal. Claude Desktop can run `nim_get_container_logs` to pull stdout logs directly into your chat, saving you from digging through raw system outputs.

Inspect physical GPU memory and loaded models

Query physical limits directly with `nim_get_gpu_status` to see exactly what hardware your machine has available. Your agent uses this data to map topological limits and check active memory variables without leaving the chat. You can also run `nim_list_models` to see which active LLMs are currently available on your backend. This gives you exact configuration bounds and engines from `nim_get_metadata` before you run heavy inference tasks.

Scale container replicas on the fly

Adjust your container setup on the fly using `nim_scale_replicas` when traffic spikes or queues back up. This MCP Server lets you adjust active hardware replication assignments instantly based on real-time demands. Your agent uses `nim_get_metrics` to pull Prometheus telemetry first. It keeps your local hardware running hot only when it's absolutely necessary, saving power and thermal headroom.

Setup guide

Set up NVIDIA NIM MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The NVIDIA NIM MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the NVIDIA NIM MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under nvidia-nim-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 Claude Desktop

Open your Claude Desktop configuration file and add the MCP Server definition under the mcpServers key. Restart the application, and you will see the tools available via the hammer icon in your chat window.

Yes, when you ask your agent to manage scaling. The agent reads live Prometheus data using `nim_get_metrics` and triggers `nim_scale_replicas` to adjust active hardware instances based on your current workload.

The agent runs `nim_check_health_live` to verify the container host is responsive. It then uses `nim_check_health_ready` to ensure the specific GPU inference layers have successfully loaded your model weights.

You need standard access to the container host socket or API endpoint where your containers run. The MCP Server communicates over standard stdio transport to execute commands on your behalf.

All data stays on your local machine. The server reads container stdout logs and GPU memory metrics locally, sending them only to your local chat client without routing raw infrastructure data to external third-party servers.

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