Provides tools for interacting with NVIDIA NIM and Visual GenAI APIs, including checking API configuration, listing available models, running chat completions, and generating images through NVIDIA-hosted endpoints.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@NVIDIA MCP list available NVIDIA models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Local MCP server for NVIDIA NIM and Visual GenAI APIs. It exposes small, practical tools for:
checking NVIDIA API configuration
listing available NVIDIA models
running chat completions through NVIDIA-hosted LLMs
generating images through NVIDIA hosted Visual GenAI endpoints
This repository is a personal MCP wrapper. It does not contain an NVIDIA API key and does not run image generation locally; the MCP process runs on the local machine and calls NVIDIA-hosted APIs for inference.
The server does not store secrets in this repository.
It loads environment variables from:
NVIDIA_MCP_ENV_FILE, when provided
this repository's .env, when present
process environment variables
Supported key names:
NVIDIA_API_KEY
NGC_API_KEY
NVIDIA_KEY
nvidia-key
nvidia-key is accepted for compatibility with an existing local .env, but NVIDIA_API_KEY is preferred for new setups.
Related MCP server: NVIDIA NIM MCP Server
Example:
[mcp_servers.nvidiaMcp]
command = "node"
args = ["/path/to/minsoo-nvidia-mcp/src/server.mjs"]
env_vars = ["NVIDIA_API_KEY", "NGC_API_KEY", "NVIDIA_KEY"]
[mcp_servers.nvidiaMcp.env]
NVIDIA_MCP_ENV_FILE = "/path/to/.env"
NVIDIA_MCP_OUTPUT_DIR = "/path/to/minsoo-nvidia-mcp/output"The current default image endpoint is:
https://ai.api.nvidia.com/v1/genai/black-forest-labs/flux.2-klein-4bThe MCP uses short, direct, one-paragraph prompts best for FLUX-style image generation. Avoid committing generated images unless they are intentionally part of an example or release artifact.
Image generation defaults to dry_run=true so a tool call can preview the request without consuming API credits. Set dry_run=false only when you intentionally want to generate an image.
Before publishing:
keep .env untracked
keep node_modules/ untracked
keep output/ untracked unless intentionally publishing sample output
commit .env.example, not a real key file
Run a non-streaming chat completion through NVIDIA's OpenAI-compatible API.
Inputs: prompt (required), model, max_tokens, temperature, +2 more.
Check whether the NVIDIA MCP can see an API key and which base URLs/output directory it will use.
Inputs: probe.
Generate an image through NVIDIA's OpenAI-compatible image generation API. Defaults to dry_run=true to avoid accidental credit usage.
Inputs: prompt (required), n, size, force, +3 more.
List models visible to the configured NVIDIA API key.
Inputs: limit, filter.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool targets a distinct function: chat completion, setup verification, image generation, and model listing. No overlap in purposes.
All tools use snake_case with clear verb-noun structure: chat_completion, check_nvidia_setup, generate_image, list_models. Perfectly consistent.
Four tools is well-scoped for a wrapper around NVIDIA's API, covering essential operations without unnecessary bloat.
Covers core operations but lacks streaming completions and embeddings, which are common in similar APIs. The generate_image tool also has limited visible parameters.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
List models, read model details and send chat messages in Cerebras.
Generate images, videos and music with model discovery, cost estimates and asynchronous results.
Provides YouCam API for AI image and video editing and generation.