How to Use the NVIDIA API Catalog MCP in Cursor

Q: How do I add the NVIDIA API Catalog MCP Server to Cursor?

Add the MCP server configuration to your project's .cursor/mcp.json file. Provide your API token in the environment variables, then enable Agent mode in the Cursor chat panel.

Q: Can Cursor generate vectors using the NVIDIA API Catalog?

Yes, Cursor uses the nvidiagenerateembeddings tool to send code blocks or text chunks to NVIDIA's embedding models, returning raw vectors directly to your workspace using standard MCP protocols.

Q: How do I check my NVIDIA API Catalog quota inside Cursor?

Ask the Cursor agent to check your limits. It will execute nvidiachecktokenquota to fetch your real-time developer credits and print them directly in the chat panel.

Q: Can I use this server to summarize large codebase files?

Yes. The nvidiasummarizecontent tool allows Cursor to compress long files, documentation, or logs into concise summaries without blowing through your prompt token limits.

Code with NVIDIA API Catalog models natively in Cursor to generate embeddings and run completions inside your files.

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 Cursor

Create your Vinkius account to connect NVIDIA API Catalog to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate Code Embeddings Directly in Cursor

The `nvidia_generate_embeddings` tool maps unstructured code files into vector representations directly within Cursor using this MCP connection. You can build high-dimensional vector representations of your local codebase files without leaving your editor. The Cursor agent reads your workspace files, runs the embedding generation through NVIDIA's optimized pipeline, and structures the vectors. You can immediately feed these embeddings into your local retrieval systems.

Run Fast Model Completions in Your Editor

The `nvidia_chat_completion` tool executes rapid model inference over Nemotron and Llama3 models inside your Cursor editor. The Agent mode pipes your active file context straight to NVIDIA's cloud infrastructure for rapid code generation. If you want to check which models are currently available to your key, ask Cursor to run `nvidia_list_foundation_models`. It returns the active endpoints so you can swap models on the fly.

Debug Visual UI Bugs inside Cursor

The `nvidia_vision_inference` tool processes UI screenshots inside Cursor to detect visual bugs. Drop a UI screenshot into the chat and ask the agent to find bugs using NVIDIA's hosted vision models. The Cursor agent takes the visual analysis, matches it against your active source code files, and suggests direct code fixes right in your editor.

Setup guide

Set up NVIDIA API Catalog MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the NVIDIA API Catalog MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent NVIDIA API Catalog transactions." If the MCP tools are loaded correctly, Cursor will call the NVIDIA API Catalog tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

Add the MCP server configuration to your project's `.cursor/mcp.json` file. Provide your API token in the environment variables, then enable Agent mode in the Cursor chat panel.

Yes, Cursor uses the `nvidia_generate_embeddings` tool to send code blocks or text chunks to NVIDIA's embedding models, returning raw vectors directly to your workspace using standard MCP protocols.

Ask the Cursor agent to check your limits. It will execute `nvidia_check_token_quota` to fetch your real-time developer credits and print them directly in the chat panel.

Yes. The `nvidia_summarize_content` tool allows Cursor to compress long files, documentation, or logs into concise summaries without blowing through your prompt token limits.

No. Your raw source code blocks and vector arrays processed by `nvidia_generate_embeddings` are sent securely to NVIDIA's endpoints. The MCP server runs in an ephemeral sandbox that destroys all session data immediately after 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