# NVIDIA AI CKG

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

- name: io.github.Yarmoluk/ckg-nvidia-ai
- version: 0.16.4
- connection class: unknown (unknown)
- trust: 61/100
- quality: 76/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Yarmoluk%2Fckg-nvidia-ai
- tools: https://api.protogrid.dev/v1/servers/io.github.Yarmoluk%2Fckg-nvidia-ai/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

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


## Trust

- hygiene: 100
- liveness: 0
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo -unreachable(12 failures) ~updated-83d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 76/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_domains (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); query_ckg (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_prerequisites (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,543 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history not recorded yet

### dependencies: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 30 resolved packages
- pass `deps.mcp_sdk_version`: mcp 1.30.0, no known advisory
- pass `deps.resolvable`: ckg-nvidia-ai@0.16.4 resolved: 30 packages

- tools: 9, about 1,543 tokens to load them all
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Yarmoluk/ckg-nvidia-ai.svg)](https://protogrid.dev/servers/io.github.Yarmoluk/ckg-nvidia-ai)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- pypi ckg-nvidia-ai@0.16.4: resolved, 29 dependencies, MCP SDK mcp 1.30.0

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://ckg-nvidia-ai.onrender.com/mcp (streamable-http, auth none, reachable false, uptime30d 0.47826087)

## Packages

- pypi ckg-nvidia-ai@0.16.4

## Tools (9)

- `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.
    
- `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().
    
- `list_domains`: List all 20 NVIDIA AI domains available in this knowledge graph.
- `list_ecosystem`: Discover other CKG packages for adjacent domains — finance, healthcare, legal, and more.
- `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).
    
- `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.
    
- `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.
    
- `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'.
    
- `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'.