MCP.Market

Nvidia Nim MCP server

by david-eve-za·io.github.david-eve-za/nvidia-nim-mcp·v2.1.2·1 stars
No reviews yet

MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking

C63/100grade C
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
C63/100

full report

Adoption
Growing

1 stars62 downloads/wk

Reviews

Write one

Nobody has reviewed Nvidia Nim yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Nvidia Nim tools (11, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze_image

    Analyze and describe images using NVIDIA NIM vision and multimodal models. Provide an image URL and a prompt/question to get detailed analysis, captioning, or visual Q&A.

  • chat_completionwrite action

    Send a multi-turn conversation to a NVIDIA NIM language model and receive a completion. Supports all major open-source LLMs including Llama 3.1, Mistral, Gemma, Qwen, and more.

  • compare_models

    Compare 2-5 models side-by-side across key decision factors: licensing, hardware requirements, benchmarks, capabilities, and use case tags. Returns structured comparison table.

  • create_embeddingswrite action

    Convert text(s) into vector embeddings using NVIDIA NIM embedding models. Useful for semantic search, RAG, clustering, and similarity comparisons.

  • function_calling

    Use NIM models with tool/function calling capabilities. The model will decide which function to call and with what arguments.

  • generate_image

    Generate images from text prompts using NVIDIA NIM image generation models (Stable Diffusion XL, SDXL Turbo, SD3, FLUX.1). Supports various resolutions, samplers, and schedulers. FLUX.1-schnell and FLUX.1-kontext-dev are available on the free NVIDIA AI Foundation tier. Can save generated images as PNG files to disk.

  • get_model_info

    Get detailed information about a specific NVIDIA NIM model.

  • list_models

    List available NVIDIA NIM models with detailed metadata for agent selection, optionally filtered by category (language, embedding, reranking, vision, code, multimodal, image_generation) and advanced filters.

  • multimodal_task

    Perform multimodal tasks combining text and images. Send a conversation with mixed text and image content to multimodal models for complex reasoning across modalities.

  • rerank_passages

    Rerank a list of passages by relevance to a query using NVIDIA NIM reranking models. Essential for RAG pipelines to improve retrieval quality.

  • text_generation

    Generate text from a single prompt (simplified interface). Ideal for one-shot tasks like summarization, translation, extraction, or Q&A.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

2 medium
  • Code scan15 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 40 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumnpm install lifecycle script presentinstall.script
  • mediumnpm install lifecycle script presentinstall.script
    package.json: …de scripts/verify-installation.js", "postinstall": "node scripts/postinstall.js" }, "k…
Overall 63/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Nvidia Nim compares

Against every graded Media MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
63/100
higher than 18% of 1,337 Media servers
Tools
11
the typical Media server has 7
Tools that change things
18%
typical: 4%. Fewer write tools means less an agent can break
GitHub stars
1
more than 55% of 715 Media servers
Downloads a week
62
more than 48% of 365 Media servers with a package

What its tools let an agent do: 8 read · 2 create · 1 change

Install Nvidia Nim in Claude Code, Cursor or VS Code

Runs npx -y nvidia-nim-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add nvidia-nim-mcp -- npx -y nvidia-nim-mcp
Add to Cursor

What the publisher says

From the Nvidia Nim repository's README, as published. We do not edit it. Read it on GitHub

NVIDIA NIM MCP Server

A production-ready Model Context Protocol (MCP) server for consuming NVIDIA NIM (NVIDIA Inference Microservices) models. Supports 50+ LLMs, multimodal models, image generation, embeddings, reranking, function calling, vision, and code-specialized models with rich metadata for intelligent agent selection.

🚀 Features

  • 10 MCP Tools: chat completion, text generation, embeddings, reranking, function calling, model listing, model info, image generation, image analysis, multimodal tasks, model comparison
  • 50+ Supported Models: Llama 3.1/3.2, Nemotron 3 Ultra (550B), MiniMax M3, Kimi K2.6 (1T), DeepSeek V4 Pro, GLM 5.1, Qwen 3.5 397B, Mistral Large 3 (675B), GPT-OSS 120B, DiffusionGemma, FLUX.1, SDXL, SD3, and more
  • Rich Model Metadata: licensing, hardware requirements, benchmarks, image generation specs, reasoning modes, tags for agent selection
  • Advanced Filtering: by commercial use, reasoning, vision, function calling, multimodal, context length, tags, hardware
  • Production-Grade: automatic retries with exponential backoff, per-minute rate limiting, structured JSON logging
  • Type-Safe: full TypeScript, Zod input validation on every tool
  • Docker-Ready: multi-stage Dockerfile with non-root user, health checks
  • Configurable: all settings via environment variables
  • Single Required Env: Only NVIDIAAPIKEY required; all others have sensible defaults

📋 Prerequisites

  • Node.js 18+ (for NPM installation) or Docker (for container deployment)
  • A NVIDIA NGC API key (nvapi-...)

⚙️ Installation

Option 1: NPM Global Installation (Recommended)

# Install globally
npm install -g nvidia-nim-mcp

# Run directly
nvidia-nim-mcp

Option 2: NPM Local Installation

# Initialize your project
npm init -y

# Install locally
npm install nvidia-nim-mcp

# Run with npx
npx nvidia-nim-mcp

Option 3: From Source

# Clone / download the project
cd nvidia-nim-mcp

# Install dependencies
npm install

# Build TypeScript
npm run build

Option 4: Docker

# Pull from Docker Hub (when published)
docker pull nvidia-nim-mcp

# Or build locally
docker build -t nvidia-nim-mcp .

🔑 Configuration

Copy .env.example to .env and fill in your API key:

cp .env.example .env

Only NVIDIAAPIKEY is required — all other variables have production-ready defaults:

🚀 Running

NPM Global Installation

# Run the server
nvidia-nim-mcp

# With custom environment variables
NVIDIA_API_KEY=nvapi-your-key LOG_LEVEL=debug nvidia-nim-mcp

NPM Local Installation

# Run with npx
npx nvidia-nim-mcp

# Or add to package.json scripts
# "scripts": { "start": "nvidia-nim-mcp" }
npm start

From Source

# Development mode with auto-reload
npm run dev

# Production mode (compiled)
npm run build && npm start

Docker

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Nvidia Nim: common questions

Is Nvidia Nim MCP server safe?
With care: it is graded C, so read the findings first (63/100). Read the Nvidia Nim safety report
How do I install Nvidia Nim?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Nvidia Nim need an API key?
Yes. The registry entry asks for NVIDIA_API_KEY.
Is Nvidia Nim maintained?
The last commit was 79 days ago (2026-08-17). The latest release is v2.1.2.
What can I use instead of Nvidia Nim?
Servers from other publishers that do the same job: Remove AI Watermarks MCP server, Transloadit Media Processing MCP server and SuperCMO MCP server.
How does Nvidia Nim compare with other Media MCP servers?
safety score 63/100 (higher than 18% of 1,337 Media servers); tools 11 (the typical Media server has 7); tools that change things 18% (typical: 4%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Nvidia Nim

Same job from other publishers: the closest match first, then the best rated.

  • Remove AI Watermarks
    Identify and remove AI watermarks and provenance metadata from your own images and video.
    A
  • Transloadit Media Processing
    Process video, audio, images and documents with Transloadit Robots. Connect by URL with OAuth.
    A
  • SuperCMO
    Marketing media generation — image, video, voice — for AI agents. BYO keys.
    B
  • three.ws Vision
    Image understanding for AI agents — analyze and describe any image via the three.ws pipeline.
    More from nirholas →
    A
  • Midjourney
    MCP server for Midjourney AI image generation and editing
    More from AceDataCloud →
    A