io.github.Yarmoluk/ckg-nvidia-ai

up checked 2026-11-11T07:37:55.598Z

Unclaimed · Unverified

Publisher-provided title

NVIDIA AI CKG

Publisher-provided description

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

Summary by lookupd

Queries a graph of NVIDIA AI concepts to find prerequisites, related concepts, domains, and source provenance hashes; includes a local…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http ckg-nvidia-ai https://ckg-nvidia-ai.onrender.com/mcp

Claude Code, pypi package (stdio)

claude mcp add ckg-nvidia-ai -- uvx ckg-nvidia-ai

Codex, remote (streamable-http)

codex mcp add ckg-nvidia-ai --url https://ckg-nvidia-ai.onrender.com/mcp

Codex, pypi package (stdio)

codex mcp add ckg-nvidia-ai -- uvx ckg-nvidia-ai

Cursor, remote (streamable-http) → .cursor/mcp.json

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

Cursor, pypi package (stdio) → .cursor/mcp.json

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

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

list_domains List all 21 NVIDIA AI domains available in this knowledge graph.
search_concepts Find concepts in a NVIDIA AI domain by keyword. Args: query: Search term — e.g. 'inference', 'sandbox', 'quantization', 'guardrails'. doma
query_ckg Traverse the NVIDIA knowledge graph from a concept — prerequisites and dependents. Args: concept: Concept name (partial match supported) — e.g. 'Te
get_prerequisites Return the full ordered prerequisite chain for a concept — everything to learn first. Args: concept: Target concept — e.g. 'Speculative Decoding',
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
list_ecosystem Discover other CKG packages for adjacent domains — finance, healthcare, legal, and more.
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 complex
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 (
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

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.Yarmoluk/ckg-nvidia-ai.svg)](https://lookupd.com/servers/io.github.Yarmoluk/ckg-nvidia-ai)