MCP server for NVIDIA NIM - 50+ LLMs, multimodal, image gen, embeddings, reranking
Connect Runs on your machine
claude mcp add nvidia-nim-mcp -e NVIDIA_API_KEY=<NVIDIA_API_KEY> -e NVIDIA_NIM_BASE_URL=<NVIDIA_NIM_BASE_URL> -e NVIDIA_AI_FOUNDATION_URL=<NVIDIA_AI_FOUNDATION_URL> -e DEFAULT_MODEL=<DEFAULT_MODEL> -e ENABLE_IMAGE_GENERATION=<ENABLE_IMAGE_GENERATION> -e ENABLE_VISION=<ENABLE_VISION> -e ENABLE_MULTIMODAL=<ENABLE_MULTIMODAL> -- npx -y [email protected]{
"mcpServers": {
"nvidia-nim-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"NVIDIA_API_KEY": "<NVIDIA_API_KEY>",
"NVIDIA_NIM_BASE_URL": "<NVIDIA_NIM_BASE_URL>",
"NVIDIA_AI_FOUNDATION_URL": "<NVIDIA_AI_FOUNDATION_URL>",
"DEFAULT_MODEL": "<DEFAULT_MODEL>",
"ENABLE_IMAGE_GENERATION": "<ENABLE_IMAGE_GENERATION>",
"ENABLE_VISION": "<ENABLE_VISION>",
"ENABLE_MULTIMODAL": "<ENABLE_MULTIMODAL>"
}
}
}
}{
"mcpServers": {
"nvidia-nim-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"NVIDIA_API_KEY": "<NVIDIA_API_KEY>",
"NVIDIA_NIM_BASE_URL": "<NVIDIA_NIM_BASE_URL>",
"NVIDIA_AI_FOUNDATION_URL": "<NVIDIA_AI_FOUNDATION_URL>",
"DEFAULT_MODEL": "<DEFAULT_MODEL>",
"ENABLE_IMAGE_GENERATION": "<ENABLE_IMAGE_GENERATION>",
"ENABLE_VISION": "<ENABLE_VISION>",
"ENABLE_MULTIMODAL": "<ENABLE_MULTIMODAL>"
}
}
}
}{
"servers": {
"nvidia-nim-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"NVIDIA_API_KEY": "<NVIDIA_API_KEY>",
"NVIDIA_NIM_BASE_URL": "<NVIDIA_NIM_BASE_URL>",
"NVIDIA_AI_FOUNDATION_URL": "<NVIDIA_AI_FOUNDATION_URL>",
"DEFAULT_MODEL": "<DEFAULT_MODEL>",
"ENABLE_IMAGE_GENERATION": "<ENABLE_IMAGE_GENERATION>",
"ENABLE_VISION": "<ENABLE_VISION>",
"ENABLE_MULTIMODAL": "<ENABLE_MULTIMODAL>"
}
}
}
}Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
NVIDIA_API_KEYRequired, secret | Your NVIDIA API key for accessing NIM models. Get one at https://build.nvidia.com |
NVIDIA_NIM_BASE_URLOptional | Base URL for self-hosted NIM endpoints |
NVIDIA_AI_FOUNDATION_URLOptional | Base URL for NVIDIA AI Foundation Models (free tier available) |
DEFAULT_MODELOptional | Default model to use for chat/text generation |
ENABLE_IMAGE_GENERATIONOptional | Enable image generation tools |
ENABLE_VISIONOptional | Enable vision/image analysis tools |
ENABLE_MULTIMODALOptional | Enable multimodal tools |
Details
| Package | [email protected] (NPM, stdio) |
| First published | 26 Jun 2026 |
| Last updated | 26 Jun 2026 |
| Registry name | io.github.david-eve-za/nvidia-nim-mcp |
More ai and media servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.