NVIDIA AI CKG

io.github.YarmolukPublished by GitHub account Yarmolukv0.16.4Updated Oct 24, 2026

NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.

The publisher's own server: NVIDIA CUDA Docs

VerifiedStreamable HTTPWeb executableKnowledge & MemoryAI & ML

Overview

AI-generated overview

Provides an assistant with NVIDIA AI knowledge graphs spanning 20 domains, with provenance hashing and token-efficient retrieval.

What you can do
Exposes NVIDIA AI knowledge graphs covering 20 domains through the Model Context Protocol. The description advertises 4x F1 and 11x fewer tokens, plus SHA-256 provenance for retrieved content. No individual tools are listed in the manifest, so the exact operations are not documented here.
When to use it
Consider it when an assistant needs structured NVIDIA AI domain knowledge and token-efficient retrieval with provenance. It is less useful if you need documented tool names or a specific data source that is not among the 20 domains.
Requirements
Can be used as a remote streamable HTTP endpoint or run locally as the PyPI package ckg-nvidia-ai via uvx over stdio. No authentication, environment variables, or headers are declared.
Before you install
The manifest declares no authentication, environment variables, or headers, so no credentials are requested. The tool list is not published, so review what the server actually exposes before relying on it. Retrieval results are sent to the remote endpoint when using the hosted option.

Installation

In SourceWeft

  1. Open NVIDIA AI CKG in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Yarmoluk%2Fckg-nvidia-ai/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "nvidia-ai-ckg": {
      "type": "http",
      "url": "https://ckg-nvidia-ai.onrender.com/mcp"
    }
  }
}

README

This repository has no README.

Tools

9

list_domains

List all 20 NVIDIA AI domains available in this knowledge graph.

Takes no parameters.

search_concepts

Find concepts in a NVIDIA AI domain by keyword. Args: query: Search term — e.g. 'inference', 'sandbox', 'quantization', 'guardrails'. domain: Domain name from list_domains() — e.g. 'nvidia-nim', 'nvidia-openshell'.

Parametersqueryrequireddomainrequired

query_ckg

Traverse the NVIDIA knowledge graph from a concept — prerequisites and dependents. Args: concept: Concept name (partial match supported) — e.g. 'TensorRT', 'NIM', 'Isaac Lab'. domain: Domain name from list_domains() — e.g. 'nvidia-tensorrt-triton', 'nvidia-isaac'. depth: Traversal depth 1–5 (default 3).

Parametersdepthdomainrequiredconceptrequired

get_prerequisites

Return the full ordered prerequisite chain for a concept — everything to learn first. Args: concept: Target concept — e.g. 'Speculative Decoding', 'Isaac Lab', 'NeMo Guardrails'. domain: Domain name from list_domains().

Parametersdomainrequiredconceptrequired

ask_nvidia

Ask a natural-language question answered by Qwen grounded on the NVIDIA CKG. Requires Ollama running locally with a Qwen model pulled: ollama pull qwen2.5:14b Override model: NVIDIA_CKG_MODEL env var (default: qwen2.5:14b) Override host: NVIDIA_CKG_OLLAMA env var (default: http://localhost:11434) Args: question: Natural-language question about the NVIDIA AI stack. domain: Domain from list_domains() — auto-detected from question if omitted.

Parametersdomainquestionrequired

list_ecosystem

Discover other CKG packages for adjacent domains — finance, healthcare, legal, and more.

Takes no parameters.

route_query

Route an NVIDIA AI question to the optimal model and reasoning approach via graph depth. The CKG graph IS the router — hop depth is a deterministic complexity metric. Deeper NVIDIA prerequisite chains (CUDA → TensorRT → TensorRT-LLM → NIM) require more capable models. No heuristic: the graph decides. Routing table: hop_depth 1 → haiku · direct (simple lookup) hop_depth 2 → sonnet · generic_cot (moderate chain) hop_depth 3+ → opus · sparql_cot (deep dependency, structured reasoning) Args: question: Concept name or natural language question about NVIDIA AI. domain: Domain from list_domains() — e.g. "nvidia-tensorrt-triton", "nvidia-nim". Returns: model_tier + reasoning_approach + why + context subgraph to inject before LLM call.

Parametersdomainquestionrequired

verify_source

Return the source URL and SHA-256 content hash for any NVIDIA AI concept node. Audit chain: edge answer → graph commit → source_content_hash → source_url (fetch hint). Verification: curl -s <source_url> | sha256sum # compare to source_hash Args: concept: Concept label (partial match supported). domain: Domain from list_domains() — e.g. 'nvidia-nim', 'nvidia-tensorrt-triton'.

Parametersdomainrequiredconceptrequired

query_intersect

Answer a conjunctive query: concepts reachable from EVERY anchor at once (A AND B). query_ckg walks outward from one concept. This intersects the reachable sets of two or more, which is the shape of most real questions — "the component that satisfies A AND applies to B". Neither anchor alone answers it; the answer lives in the overlap. Every branch is an exact set of declared edges, so the intersection is exact. A concept appears only if a declared path reaches it from each anchor. A relation missing from the graph produces an empty result, never a guess. Args: branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes everything within `depth` hops, or an anchor plus an explicit relation path using '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the frontier. '*' matches any relation. Mix both forms freely. domain: Domain name from list_domains(). depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths. direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default). mode: 'AND' (default) intersects branches; 'OR' unions them. limit: Max concepts listed, 1-200 (default 40). The true count is always shown. Returns: Markdown with the query plan and its per-step set sizes, then the answer set with taxonomy tags. Reports which branch was empty when the intersection is empty.

Parametersmodedepthlimitdomainrequiredbranchesrequireddirection

Version history

1
  1. v0.16.4LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.

Other Nvidia integrations

NVIDIA CUDA Docs

com.nvidia.ngc.nsight.copilot.apiOfficial publisher

A remote MCP endpoint that lets AI coding agents search NVIDIA CUDA documentation and code samples.

Streamable HTTPWeb executableAuth
Knowledge & MemoryCredential requiredOct 25, 2026

Nvidia Nim Mcp

Published by GitHub account david-eve-za

Local MCP server that connects an assistant to NVIDIA NIM models for chat, text generation, embeddings, reranking, image generation and vision tasks.

STDIODesktop only
Media & DesignNot validated yetOct 24, 2026

NVIDIA NemoClaw CKG

Published by GitHub account Yarmoluk

A knowledge-graph server for NVIDIA NemoClaw that lets an assistant answer questions, trace prerequisites and verify sources across 55 typed concept nodes.

Streamable HTTPWeb executable
Knowledge & Memory8 toolsOct 27, 2026

NVIDIA Elements

Published by GitHub account NVIDIA

NVIDIA Elements MCP server that gives an assistant the Elements UI design system's component APIs, tokens, examples and project tooling.

STDIODesktop only
Developer ToolsNot validated yetNov 3, 2026