MCP.so
Sign In

CKG-NVIDIA- AI - Nvidia Developer Stack As A Compressed Knowledg…

@Yarmoluk

Repository

About CKG-NVIDIA- AI - Nvidia Developer Stack As A Compressed Knowledg…

NVIDIA AI developer stack as a Compressed Knowledge Graph (CKG) — 20 domains, 998 nodes, every prerequisite chain declared as typed edges. Agents traverse REQUIRES/ENABLES relationships instead of scanning docs. 4× F1 vs RAG, 11× fewer tokens. No API key required

#nvidia#knowledge-graph#mcp#ai-agents#cuda#nim#tensorrt

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "nvidia-ai": {
      "command": "uvx",
      "args": [
        "ckg-nvidia-ai"
      ]
    }
  }
}

Tools

No tools detected

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is CKG-NVIDIA-AI?

CKG-NVIDIA-AI is a read-only MCP server that provides a Compressed Knowledge Graph (CKG) covering the full NVIDIA AI developer stack across 20 domains and 998 nodes. It enables AI agents to traverse typed dependency graphs instead of using retrieval, achieving higher accuracy with drastically fewer tokens.

How to use CKG-NVIDIA-AI?

Install with pip install ckg-nvidia-ai and run the MCP server via uvx ckg-nvidia-ai. Configure it in Claude Desktop, Claude Code, Cursor, or other MCP clients using the provided JSON snippets. Tools include list_domains(), search_concepts(), query_ckg(), get_prerequisites(), and ask_nvidia() (the last requires Ollama with qwen2.5:14b).

Key features of CKG-NVIDIA-AI

  • 4× F1 and 11× fewer tokens vs RAG
  • 998 nodes across 20 NVIDIA AI domains
  • Deterministic graph traversal – no hallucination
  • Read-only: never writes, mutates, or executes
  • Typed edges (REQUIRES, ENABLES, RELATES_TO, IMPLEMENTS)
  • Three-state confidence (high, null, low) for every edge

Use cases of CKG-NVIDIA-AI

  • Deploying a real-time speech AI pipeline on NVIDIA Jetson
  • Mapping the full prerequisite chain for TensorRT-LLM on Hopper GPUs
  • Understanding Clara Parabricks dependencies for whole-genome sequencing
  • Building layered architecture maps with shared prerequisites across domains
  • Auditing deployment requirements before cold-start provisioning

FAQ from CKG-NVIDIA-AI

What is a Compressed Knowledge Graph (CKG) and how does it differ from retrieval?

A CKG is a layer that converts domain documentation into structured, agent-traversable knowledge. Instead of retrieval, the agent traverses declared relationships, which costs fewer tokens and does not guess.

Is CKG-NVIDIA-AI read-only?

Yes. All tools are read-only. The server never writes, mutates, or executes anything. Every response is a declared graph traversal.

What are the dependencies and runtime requirements?

The core server only requires the mcp[cli] package. For the ask_nvidia() tool,

Frequently asked questions

What is a Compressed Knowledge Graph (CKG) and how does it differ from retrieval?

A CKG is a layer that converts domain documentation into structured, agent-traversable knowledge. Instead of retrieval, the agent traverses declared relationships, which costs fewer tokens and does not guess.

Is CKG-NVIDIA-AI read-only?

Yes. All tools are read-only. The server never writes, mutates, or executes anything. Every response is a declared graph traversal.

What are the dependencies and runtime requirements?

The core server only requires the `mcp[cli]` package. For the `ask_nvidia()` tool,

Comments

Basic information

Transports

stdio

Author

Yarmoluk

Submitted by

Daniel Yarmoluk

More MCP servers

ListingGood MCP

DedeGroup

ListingGood AI Recommendation Engine — a hosted MCP server + Claude/Cursor skills that make Amazon's AI recommend your products. Free no-login scan: https://listinggood.com/scan Get API key: https://listinggood.com/deve

1

Clipkit

clipkit-video

The video infra for AI agents: compose motion-graphics video from one JSON document (open Clipkit Protocol), validate before it costs anything, preview stills in-chat, and render deterministic MP4s on a GPU runtime.

11

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

12

Capital.com MCP

capital-com-sv

CFDs are complex instruments and come with a high risk of losing money rapidly due to leverage. 81.31% of retail investor accounts lose money when trading CFDs with this provider. You should consider whether you understa

4

Snipara

alopez3006

MCP connector for Snipara, the Project Brain for AI coding agents

1