How to Use the NVIDIA AI MCP in Windsurf

Q: How does Cascade use the NVIDIA AI MCP Server to write code?

Cascade calls generatecode directly when you describe a feature in the chat panel. It takes your prompt, sends it to the NVIDIA API Catalog, and writes the resulting code block directly into your active editor file.

Q: Can I switch models during a Windsurf session with NVIDIA AI?

Yes. You can tell Cascade to use chatcompletion with specific models like Llama 3.1 70B or Mistral Large. Windsurf handles the connection properties automatically so you can swap models mid-conversation.

Q: Does this server support semantic search indexing in Windsurf?

It does. Cascade can use the getembeddings tool to generate vector representations of your local files using the nv-embed-v1 model, making it easier to search your codebase semantically.

Run NVIDIA AI reasoning models directly inside Windsurf to let Cascade write, test, and refactor code autonomously.

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 Windsurf

Create your Vinkius account to connect NVIDIA AI to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run massive NVIDIA AI models inside Cascade

Let Cascade query the massive 405B parameter model using `ask_question` to map out complex application architectures. Instead of bouncing between browser tabs, your Windsurf agent pulls raw reasoning power directly into your workspace to plan multi-step refactoring jobs. Once Cascade outlines the plan, it instantly invokes `chat_completion` to swap in specific models like Llama-3 or Mistral for targeted code edits. The agent handles the model selection and token boundaries behind the scenes while you watch the codebase update in real time.

Automate database migrations with this MCP Server

Windsurf can inspect your local schema and run `text_to_sql` to generate complex database queries without manual drafting. When Cascade encounters a broken database migration, it automatically calls this tool to write clean SQL that matches your exact PostgreSQL or MySQL dialect. After generating the query, the agent uses `generate_code` to write the accompanying repository layer in your active language. This keeps your data models and your application code perfectly synchronized without leaving your IDE.

Analyze and translate localized content on the fly

This MCP Server lets Cascade scan your internationalization files and use `translate_text` to generate accurate translations across your entire UI. If you are dealing with user feedback loops, Cascade chains this tool with `analyze_sentiment` to flag negative reviews directly in your workspace. This lets Windsurf automatically sort incoming support tickets by urgency based on the computed emotional tone. You get a fully automated triage system running locally inside your editor without writing any custom API glue.

Setup guide

Set up NVIDIA AI MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my NVIDIA AI payment history." If connected, Cascade will call the NVIDIA AI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Cascade calls `generate_code` directly when you describe a feature in the chat panel. It takes your prompt, sends it to the NVIDIA API Catalog, and writes the resulting code block directly into your active editor file.

Yes. You can tell Cascade to use `chat_completion` with specific models like Llama 3.1 70B or Mistral Large. Windsurf handles the connection properties automatically so you can swap models mid-conversation.

Just open your Settings, go to Cascade, and find the MCP section to paste your credentials. Windsurf will instantly discover all nine tools and register them to your active workspace.

It does. Cascade can use the `get_embeddings` tool to generate vector representations of your local files using the nv-embed-v1 model, making it easier to search your codebase semantically.

Your local source code and text inputs are sent directly to the NVIDIA API Catalog via Vinkius's secure, zero-trust sandbox. No data is cached or used for training on our servers, ensuring your intellectual property remains private.

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