How to Use the NVIDIA API Catalog MCP in VS Code Copilot

Q: How do we roll out the NVIDIA API Catalog MCP Server to our VS Code Copilot team?

Commit the server configuration to your project's .vscode/mcp.json file. Once your team members pull the latest git changes, VS Code Copilot will automatically register the MCP tools.

Q: Can VS Code Copilot check our NVIDIA API Catalog spending?

Yes, Copilot uses the nvidiachecktokenquota tool to pull your active credit balance and token limits, displaying them directly in the editor chat.

Q: How do we analyze UI layouts using NVIDIA API Catalog in VS Code Copilot?

Use the nvidiavisioninference tool through Copilot Chat. Pass your local image files or screenshots to have NVIDIA's vision models analyze the visual structure.

Q: Does this integration support custom fine-tuned models?

Yes. The nvidialistloraadapters tool lets VS Code Copilot scan and apply your active LoRA overrides directly to your model completion queries.

Q: How is our proprietary source code protected during inference?

All code snippets and file contexts sent to nvidiachatcompletion pass through encrypted HTTPS channels directly to NVIDIA. Vinkius executes the server inside a zero-trust, ephemeral sandbox that never stores or caches your code.

Connect VS Code Copilot to the NVIDIA API Catalog to run Llama3 inference and check quotas across your whole team.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NVIDIA API Catalog MCP to VS Code Copilot

Create your Vinkius account to connect NVIDIA API Catalog to VS Code Copilot 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 API Catalog with VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Shared NVIDIA API Catalog MCP Server Tooling for Teams

The NVIDIA API Catalog MCP server integrates `nvidia_chat_completion` and `nvidia_list_foundation_models` directly into VS Code Copilot for team-wide access. Every developer on the project gets instant access to NVIDIA's foundational models through Copilot Chat. This setup avoids the need for individual developers to write custom API wrappers. They can query Nemotron or Llama3 models using shared configurations committed directly to your git repository.

Compress Logs and Docs in VS Code Copilot

The `nvidia_summarize_content` tool compresses long files and build logs directly within VS Code Copilot. Ask Copilot Chat to condense the file to extract the exact error trace from thousands of lines of output. The tool uses NVIDIA's optimized summarization models to parse massive text files. It returns a concise breakdown directly in the Copilot Chat panel, saving you from scrolling through terminal output.

Monitor API Latency and Quotas in VS Code

The `nvidia_check_token_quota` tool tracks your active API credit limits directly inside VS Code Copilot via the MCP protocol. This keeps your team's API costs under control by checking usage limits directly in VS Code Copilot. If you suspect a slowdown, ask Copilot to run `nvidia_get_cloud_status`. It pings the NVIDIA endpoints and returns real-time latency metrics to help you determine if the cloud hosting is lagging.

Setup guide

Set up NVIDIA API Catalog MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the NVIDIA API Catalog MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the NVIDIA API Catalog tools listed. Try asking: "List my recent NVIDIA API Catalog transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "nvidia-api-catalog-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 API Catalog. 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 API Catalog 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 API Catalog MCP in VS Code Copilot

Commit the server configuration to your project's `.vscode/mcp.json` file. Once your team members pull the latest git changes, VS Code Copilot will automatically register the MCP tools.

Yes, Copilot uses the `nvidia_check_token_quota` tool to pull your active credit balance and token limits, displaying them directly in the editor chat.

Use the `nvidia_vision_inference` tool through Copilot Chat. Pass your local image files or screenshots to have NVIDIA's vision models analyze the visual structure.

Yes. The `nvidia_list_lora_adapters` tool lets VS Code Copilot scan and apply your active LoRA overrides directly to your model completion queries.

All code snippets and file contexts sent to `nvidia_chat_completion` pass through encrypted HTTPS channels directly to NVIDIA. Vinkius executes the server inside a zero-trust, ephemeral sandbox that never stores or caches your code.

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