How to Use the NVIDIA NIM MCP in Windsurf

Q: How does Windsurf handle NVIDIA NIM container logs?

Windsurf uses nimgetcontainerlogs to pull standard output proxies directly from the orchestrator. You see the raw execution stream inside your chat panel to troubleshoot errors fast.

Q: Can Windsurf scale my NVIDIA NIM deployment?

Yes, you can instruct Cascade to trigger nimscalereplicas based on your current hardware constraints. It adjusts the execution layers to match your throughput needs.

Use the NVIDIA NIM MCP server to let Windsurf manage your GPU inference containers and hardware telemetry directly in the IDE.

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 Windsurf

Create your Vinkius account to connect NVIDIA NIM 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 NIM with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated GPU observability for Windsurf

Cascade uses `nim_get_gpu_status` to pull real-time VRAM and thermal data straight from your inference host. You get a clear view of hardware limits without leaving your editor. It connects to `nim_get_metrics` so your agent can see how models perform under load. This lets you debug performance bottlenecks before they hit production.

Model management inside Windsurf

The `nim_list_models` tool gives your agent a full list of active inference targets. It knows exactly which models are ready for deployment without manual checks. When you need to adjust capacity, `nim_scale_replicas` lets Cascade change your deployment footprint. It handles the heavy lifting while you focus on the code.

Instant health verification

Windsurf runs `nim_check_health_live` to confirm your containers are responsive. If something hangs, the agent knows immediately. It verifies readiness with `nim_check_health_ready` before pushing changes. This prevents deployment errors by ensuring the GPU layers have actually loaded your model artifacts.

Setup guide

Set up NVIDIA NIM 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 NIM 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 NIM payment history." If connected, Cascade will call the NVIDIA NIM tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Windsurf uses `nim_get_container_logs` to pull standard output proxies directly from the orchestrator. You see the raw execution stream inside your chat panel to troubleshoot errors fast.

Yes, you can instruct Cascade to trigger `nim_scale_replicas` based on your current hardware constraints. It adjusts the execution layers to match your throughput needs.

The server requires an active connection to your local or remote orchestrator. It needs network access to query the underlying NIM proxy for real-time telemetry.

All telemetry, including GPU status and model metadata, stays within your local environment. The MCP server only acts as a bridge for your agent to read local hardware states.

Open your MCP settings and add the server endpoint under the mcpServers configuration. Once saved, Cascade will auto-discover the tools and start monitoring your inference setup.

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