How to Use the NVIDIA AI MCP in Claude Code

Q: How does Claude Code handle model selection with NVIDIA AI?

Claude Code uses chatcompletion and passes your specified model parameters directly to the NVIDIA API. You can define the model in your terminal command to target specific Llama or Mistral variants.

Q: What is the command to add this MCP Server to Claude Code?

Just run this command: claude mcp add --transport http nvidia-ai . See the difference? It instantly registers the tools in your active shell.

Run this NVIDIA AI MCP Server directly from your terminal using Claude Code CLI.

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 Code

Create your Vinkius account to connect NVIDIA AI to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless code generation inside Claude Code

Claude Code calls `generate_code` to output clean, functional scripts directly into your terminal pipe. You can chain this CLI tool with grep or awk to feed legacy code directly into the NVIDIA API Catalog for rapid modernization. If your shell script needs to verify the structure of a database, the CLI uses `text_to_sql` to generate schema definitions on the fly. This lets you run headless database migrations during your CI/CD pipeline runs without human intervention.

Automated text processing inside Claude Code pipelines

This MCP Server allows your terminal agent to run `summarize_text` on massive log files or raw documentation. You can pipe server logs directly to the command line and get a concise summary of system errors in seconds. For international deployments, Claude Code uses `translate_text` to localize terminal outputs or documentation files. This makes it simple to generate multi-language readmes or help files directly from your build scripts.

High-performance vector embeddings for shell scripts

Claude Code can automate your data ingestion pipelines by using `get_embeddings` to generate vectors for raw text files. You can pipe markdown documentation into the tool and save the resulting vectors directly into your database. The CLI agent uses `list_models` to verify which embedding models are active before running bulk jobs. This ensures your automated scripts never break due to deprecated model endpoints in the NVIDIA catalog.

Setup guide

Set up NVIDIA AI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see nvidia-ai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest NVIDIA AI transactions." It will automatically discover and invoke the available NVIDIA AI tools.

Terminal

claude mcp add --transport http nvidia-ai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the NVIDIA AI MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "nvidia-ai-mcp": {
      "type": "url",
      "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 Code

Yes, you can add this MCP Server to your Claude Code configuration and run it inside GitHub Actions. The CLI will execute tools like `generate_code` headlessly based on your pipeline triggers.

Claude Code uses `chat_completion` and passes your specified model parameters directly to the NVIDIA API. You can define the model in your terminal command to target specific Llama or Mistral variants.

Just run this command: `claude mcp add --transport http nvidia-ai `. See the difference? It instantly registers the tools in your active shell.

Yes, you can pipe any CLI text output into Claude Code and let it run `analyze_sentiment`. This is useful for monitoring customer feedback logs or social media streams directly from the terminal.

Your terminal strings, code files, and raw text payloads are sent securely to the NVIDIA API Catalog. The connection is fully encrypted, and Vinkius's ephemeral sandbox ensures no logs or inputs are retained on the host.

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