How to Use the NVIDIA AI MCP in Claude

Q: How do I connect the NVIDIA AI MCP Server to Claude Desktop?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Once you save the file and restart Claude Desktop, you will see the new tools available via the hammer icon in your chat window.

Run NVIDIA AI models and generation tools directly from your Claude Desktop chat interface.

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 Claude Desktop

Create your Vinkius account to connect NVIDIA AI 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 AI with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run heavy reasoning models in Claude Desktop

The `ask_question` tool lets Claude Desktop query the 405B parameter reasoning model directly from your chat sidebar. This integration gives you heavy-duty reasoning right next to your local files. You can ask complex architectural questions or debug deep system issues. The server handles the connection to the NVIDIA API Catalog, so Claude Desktop gets the answers without you leaving the terminal or copying text back and forth.

Convert natural language to SQL queries

The `text_to_sql` tool converts plain English instructions into valid database queries directly inside Claude Desktop. Writing SQL manually is slow, especially when you need to query database schemas that you don't fully remember. Because this runs as an MCP Server, the model understands the schema context you paste into the chat. It generates the exact query you need, letting you inspect the code before running it against your local database.

Translate and summarize documents locally

The `summarize_text` and `translate_text` tools let Claude Desktop process long documents and foreign text without leaving your chat workspace. This makes handling massive log files or foreign language documentation incredibly fast. It bypasses standard rate limits by routing the heavy lifting to the API catalog. Your client gets fast summaries and accurate translations without choking your local machine's processor.

Setup guide

Set up NVIDIA AI 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 AI 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 AI 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-ai-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 Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Once you save the file and restart Claude Desktop, you will see the new tools available via the hammer icon in your chat window.

Yes, you can connect the server as a custom connector in your browser settings. Paste your remote endpoint URL into the integrations panel on claude.ai to access tools like `chat_completion` directly from the web client.

Your client can query any model hosted on the NVIDIA API Catalog. Use the `list_models` tool to see the active roster, which includes Llama and Mistral options that Claude Desktop can call for specific tasks.

When you feed customer feedback into your chat, Claude Desktop calls the `analyze_sentiment` tool to parse the text. It returns a direct emotional assessment of the text without requiring custom prompt engineering.

Your text inputs and prompts are sent directly to the NVIDIA API Catalog for processing and are never stored on Vinkius servers. Since this MCP setup runs in an ephemeral sandbox, your raw text remains isolated and secure during execution.

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