All servers · Research & knowledge · Code & repositories · AI models & agents

NVIDIA AI CKG

io.github.Yarmoluk/ckg-nvidia-ai · v0.16.4

Measured by MCP Station

Last check	Reachable
Checked at	—
Check success 7 / 30 days	—
First-try success 30 days	—
Median response	—
Lookups 30 days	—
Authentication	No auth
MCP version	2025-06-18
Rank score	—
Declared risk	Not declared (tools carry no read/destructive hints)
Capabilities declared	experimental, prompts, resources, tools
Tool definitions	9 tools · with description 100% · input schema is an object 100% · read/destructive hints 0%

Description written by the publisher, not verified

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

Connect

streamable-http · https://ckg-nvidia-ai.onrender.com/mcp

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

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

Tools as reported by the server

list_domains
List all 20 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'. domain: Domain name from list_domains() — e.g. 'nvidia-nim', 'nvidia-openshell'.
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
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().
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) Ar
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 complexity metric. Deeper NVIDIA prerequisite chains (CUDA → TensorRT → TensorRT-LLM → NIM) require more capable models. No heuristic: the graph decides
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). doma
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

Repository · JSON · Text for agents · Registry updated 2026-07-29