Nvidia Nim MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 358 installs a week from npm. Last commit 17 Aug 2026.
MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: node scripts/postinstall.js
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add nvidia-nim-mcp -e 'NVIDIA_API_KEY=<NVIDIA_API_KEY>' -- npx -y nvidia-nim-mcp{
"mcpServers": {
"nvidia-nim-mcp": {
"command": "npx",
"args": [
"-y",
"nvidia-nim-mcp"
],
"env": {
"NVIDIA_API_KEY": "<NVIDIA_API_KEY>"
}
}
}
}[mcp_servers.nvidia-nim-mcp]
command = "npx"
args = ["-y", "nvidia-nim-mcp"]
env = { NVIDIA_API_KEY = "<NVIDIA_API_KEY>" }{
"mcpServers": {
"nvidia-nim-mcp": {
"command": "npx",
"args": [
"-y",
"nvidia-nim-mcp"
],
"env": {
"NVIDIA_API_KEY": "<NVIDIA_API_KEY>"
}
}
}
}{
"servers": {
"nvidia-nim-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"nvidia-nim-mcp"
],
"env": {
"NVIDIA_API_KEY": "<NVIDIA_API_KEY>"
}
}
}
}Put your own value in place of
<NVIDIA_API_KEY> (Your NVIDIA API key for accessing NIM models. Get one at https://build.nvidia.com).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
NVIDIA_NIM_BASE_URL (Base URL for self-hosted NIM endpoints), NVIDIA_AI_FOUNDATION_URL (Base URL for NVIDIA AI Foundation Models (free tier available)), DEFAULT_MODEL (Default model to use for chat/text generation), ENABLE_IMAGE_GENERATION (Enable image generation tools), ENABLE_VISION (Enable vision/image analysis tools), ENABLE_MULTIMODAL (Enable multimodal tools).
Alternatives to Nvidia Nim MCP
same job, measured the same wayMCP server for GigaChat — AI chat, embeddings, image generation (Russia)
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
MCP server for Forge, Voxell's embedding API. Voxell's Ingot-8B-R3 ranks #1 for English on MTEB.
Geospatial AI MCP server — satellite imagery, embeddings, weather, GNS governance
30 GPU-powered AI services as MCP tools. LLM, image, video, audio, embeddings & more.
Nvidia Nim MCP — questions
Answers built from our own checks of this server.