MCP For Claude Marketplace
NVIDIA AI

NVIDIA AI MCP Connector for Claude

A+

Access LLMs, embeddings, code generation, and reasoning via NVIDIA API Catalog.

9 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect NVIDIA AI to any AI agent and harness the power of GPU-accelerated foundation models — chat with Llama, generate embeddings, write code with CodeLlama, translate text, and perform complex reasoning through the NVIDIA API Catalog.

What you can do

  • Chat with LLMs — Access Llama 3.1, Mistral, Nemotron, and more via chat completions
  • Generate Embeddings — Create vector embeddings for search and clustering
  • Code Generation — Write code from natural language prompts using CodeLlama
  • Summarization — Condense long documents into concise summaries
  • Translation — Neural translation between dozens of languages
  • Text-to-SQL — Convert natural language questions into SQL queries
  • Sentiment Analysis — Analyze the emotional tone of text
  • Complex Reasoning — Ask questions to the 405B-parameter reasoning model

How it works

  1. Subscribe to this server
  2. Enter your NVIDIA API Key (from build.nvidia.com)
  3. Start running AI models from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Developers — Prototype AI features without managing GPU infrastructure
  • Data Scientists — Generate embeddings and run NLP tasks at scale
  • Business Analysts — Use text-to-SQL to query databases with natural language
llmgpu-accelerationembeddingsmodel-inferencenatural-language-processingcode-generation

9 tools expose this connector's capabilities to your AI agent.

ask_question

Optionally provide context for better answers. Ask a question to a powerful reasoning model (405B params)

chat_completion

Use "model" to specify which AI model (e.g., "meta/llama-3.1-70b-instruct", "mistralai/mistral-large"). Messages should be in OpenAI format: [{role: "user", content: "..."}]. Chat with an NVIDIA AI model (Llama, Mistral, etc)

generate_code

Specify language if needed. Generate code from a natural language prompt

get_embeddings

Model: "nvidia/nv-embed-v1". Generate vector embeddings from text

list_models

List all available AI models on the NVIDIA API Catalog

text_to_sql

Convert natural language to SQL query

analyze_sentiment

Analyze the sentiment of a text

summarize_text

Summarize long text into a concise version

translate_text

Translate text to another language

See how to talk to your AI agent using NVIDIA AI.

Generate Python code for a REST API with FastAPI.

Generated code: `from fastapi import FastAPI app = FastAPI() @app.get('/items') async def get_items(): return {'items': []}`

Translate 'Hello, how are you?' to Japanese.

こんにちは、お元気ですか？ (Konnichiwa, ogenki desu ka?)

Summarize: The quarterly report shows revenue grew 15% YoY...

Q3 revenue increased 15% year-over-year, driven by strong demand in AI and cloud services.

The NVIDIA API Catalog offers Llama 3.1 (8B, 70B, 405B), Mistral, CodeLlama, Gemma, Nemotron, and many more. Use the `list_models` tool to see all available models.

Related Connectors

TH

Theta MCP

30 tools Official

Interact with Theta Network — query blockchain data, manage AI EdgeCloud deployments, and orchestrate decentralized video delivery.

A+ View details →
KA

Kaseya MCP

10 tools Official

Manage IT infrastructure, devices, and automation via Kaseya VSA 10.

A+ View details →
SU

Surveypal MCP

12 tools Official

Design employee experience surveys and customer feedback programs with analytics that turn responses into actionable improvements.

A+ View details →
HA

Happierleads MCP

1 tools

Connect Happierleads to any AI agent via MCP.

A+ View details →