NVIDIA NIM MCP Server
Provides tools to interact with 140+ NVIDIA NIM models for chat, embeddings, reranking, vision, image generation, OCR, and content safety via the NVIDIA API.
Click on "Install 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 NIM MCP ServerList available 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.
# @hallaxius/nvidia-nim-mcp
A Model Context Protocol (MCP) server that exposes 140+ NVIDIA NIM models to AI agents via stdio.
Supports: chat, embeddings, reranking, vision, image generation (FLUX), OCR, and content safety.
Features
Thin wrapper around
integrate.api.nvidia.com/v1andai.api.nvidia.com/v1Zero external dependencies (uses global
fetch)Bun-native, Node 20+ compatible
Offline model capability snapshot for quick lookups
Automatic fallback heuristics for unknown models
Streaming disabled by default (safe for stdio)
TypeScript strict mode with BiomeJS linting
Test suite with 23+ tests (
bun test)
Related MCP server: agents-mcp
Installation
bun add @hallaxius/nvidia-nim-mcp
# or
bunx @hallaxius/nvidia-nim-mcpQuick Setup
The fastest way to get started — configure your API key once and forget it:
# Configure your key (one-time)
bunx @hallaxius/nvidia-nim-mcp setup "nvapi-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
# Or run interactively (it will prompt for the key)
bunx @hallaxius/nvidia-nim-mcp setup
# Start the MCP server
bunx @hallaxius/nvidia-nim-mcpThe key is saved to ~/.config/nvidia-nim-mcp/config.json. Environment variables still take priority when set.
Usage
1. Set your NVIDIA API Key
You can also configure the key via environment variable:
export NVIDIA_API_KEY=nvapi-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxxSupported aliases: NVIDIA_API_KEY, NIM_API_KEY, NVAPI_KEY.
Get your key: https://build.nvidia.com/explore/discover
2. Run the MCP Server
bunx @hallaxius/nvidia-nim-mcpThe server starts over stdio and registers 9 tools.
3. Configure Your AI Agent
Integration with:
OpenCode: A global @nvidia subagent is available at ~/.config/opencode/agents/nvidia.md for querying NIM models and capabilities.
Tools
Tool | Description | Default Model |
| List all available NIM model IDs | — |
| Get model type, vision, tools, context | — |
| Chat completion with LLM |
|
| Generate text embeddings |
|
| Rank passages by query relevance |
|
| Multi-modal inference (text + images) |
|
| Generate images via FLUX |
|
| Extract text from images (OCR) |
|
| Classify text for safety |
|
Examples
List Available Models
// Agent code / MCP client usage
const models = await callTool("nim_list_models", {});
// Returns: "z-ai/glm-5.2\nmeta/llama-3.3-70b-instruct\n..."Chat Completion
const result = await callTool("nim_chat_completion", {
messages: [{ role: "user", content: "Explain quantum computing simply" }],
model: "z-ai/glm-5.2",
temperature: 0.7,
max_tokens: 2048,
});
// Returns: { content: [{ type: "text", text: "..." }] }Vision (VLM)
const result = await callTool("nim_vision_inference", {
messages: [
{
role: "user",
content: [
{ type: "text", text: "What is in this image?" },
{ type: "image_url", image_url: { url: "data:image/jpeg;base64,/9j/..." } },
],
},
],
model: "meta/llama-3.2-90b-vision-instruct",
});Embeddings
const result = await callTool("nim_create_embeddings", {
inputs: ["Hello world", "AI is amazing"],
model: "nvidia/nv-embed-v1",
});
// Returns: { embeddings: [[...], [...]], model: "nvidia/nv-embed-v1", usage: {...} }Reranking
const result = await callTool("nim_rerank_passages", {
query: "What is the capital of France?",
passages: ["Paris is the capital of France.", "Berlin is the capital of Germany.", "London is the capital of the UK."],
model: "nvidia/llama-3.2-nemoretriever-500m-rerank-v2",
});
// Returns: { results: [{ index: 0, score: 0.95 }, ...] }Image Generation (FLUX)
const result = await callTool("nim_flux_generate_image", {
prompt: "A serene mountain landscape at sunset, digital art",
width: 1024,
height: 1024,
model: "black-forest-labs/flux.1-schnell",
});
// Returns: { content: [{ type: "image", data: "<base64>", mimeType: "image/png" }] }OCR
const result = await callTool("nim_ocr_extract", {
image_path: "/absolute/path/to/screenshot.png",
// or: image_base64: "<base64 string>"
model: "nvidia/nemotron-ocr-v1",
});
// Returns: { text: "Extracted text...", detections: [{ text, confidence, bounding_box }] }Safety Classification
const result = await callTool("nim_safety_classify", {
text: "This is a harmless text.",
model: "meta/llama-guard-4-12b",
});
// Returns: { safe: true, categories: {...}, explanation: "..." }Development
Setup
bun installBuild
bun run buildType-check
bun run typecheckLint & Format
bun run lintUses BiomeJS for linting and formatting. Runs automatically before publish via prepare.
Test
bun test23+ tests covering capabilities, config, HTTP client, and server structure.
Dev mode (stdio server)
bun run devModel Capabilities
Capabilities are inferred in real-time using model ID heuristics. No static snapshot needed — the model list is fetched live from the NVIDIA API via nim_list_models.
Supported Models
140+ models across families (sourced from build.nvidia.com/models):
Category | Families |
LLM | Llama, Nemotron, DeepSeek, Qwen, GLM, Mistral, Mixtral, Gemma, Phi, GPT-OSS, MiniMax, Step, DiffusionGemma, SEED-OSS, Solar, Sarvam M, Stockmark |
VLM | Llama Vision, Nemotron VL, Phi-4 Multimodal, Cosmos, PaliGemma, MiniMax-M3, Ising Calibration |
Embeddings | NV-Embed, BGE-M3, Llama-Nemotron-Embed, ESM-2 (protein) |
Rerank | Llama-Nemotron-Rerank, Rerank-QA-Mistral |
Image Gen | FLUX.1 (dev, schnell), FLUX.2 Klein, Stable Diffusion 3.5, Qwen-Image |
OCR & Document | Nemotron OCR, Nemoretriever Parse/PAGE, PaddleOCR, NV-YOLOX |
Safety | Llama-Guard, Nemotron Safety, Nemoguard, GLiNER PII |
Audio & Speech | Whisper, Parakeet, Canary, Magpie TTS, Chatterbox TTS, Riva Translate, Studio Voice, Nemotron Voicechat |
Biology & Science | AlphaFold2, ESMFold, OpenFold2/3, Boltz-2, MolMIM, DiffDock, ProteinMPNN, RFDiffusion, Evo2, GenMol, VISTA-3D |
Physics & Simulation | CuOpt, FourCastNet, Simcenter STAR-CCM+, Fidelity, Fluent, Spectre-X |
Autonomous Driving | BEVFormer, SparseDrive, StreamPETR |
3D & Vision | TRELLIS, Relighting, EyeContact, Synthetic Video Detector |
The catalog changes — call
nim_list_modelsat runtime for the latest list.
See https://build.nvidia.com/models for the full catalog.
License
MIT © 2026 @hallaxius
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to manage Docker containers, execute commands inside them, and inspect container information through a minimalist set of tools supporting both stdio and HTTP transports.3151MIT
- Alicense-qualityDmaintenanceEnables running AI agents via OpenAI-compatible APIs with custom system prompts, models, and queries. Supports persistent memory, preset agents, and multi-step workflows like pipelines and swarms.14MIT
- Alicense-qualityCmaintenanceEnables local task execution using the user's NVIDIA NIM API quota, with tools to process file contents through LLMs, send chat prompts, and list available models.67MIT
- FlicenseAqualityBmaintenanceProvides tools for NVIDIA NIM and Visual GenAI APIs, enabling chat completions, model listing, and image generation via NVIDIA-hosted endpoints.4
Related MCP Connectors
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Generate images, video, music and voice from your CLI or AI agent. On-brand AI media toolkit.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Hallaxius/nvidia-nim-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server