NVIDIA AI CKG MCP server

• ask_nvidiaFree

  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_prerequisitesFree

  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_domainsFree

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

• list_ecosystemFree

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

• query_ckgFree

  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_intersectFree

  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_queryFree

  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_conceptsFree

  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_sourceFree

  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'.

• Code scan54 source files scanned20/25
• Live reliabilityremote reachable in 973ms20/20
• Tool poisoning9 tool descriptions checked15/15
• Auth qualityopen endpoint, read-only tools10/15
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityno repository or website to verify2/10

NVIDIA AI CKG: common questions

Is NVIDIA AI CKG MCP server safe?

Mostly: it is graded B (70/100). Read the NVIDIA AI CKG safety report

How do I install NVIDIA AI CKG?

It runs remotely at ckg-nvidia-ai.onrender.com. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.

Does NVIDIA AI CKG need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is NVIDIA AI CKG maintained?

The latest release is v0.16.4.

Is NVIDIA AI CKG up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of NVIDIA AI CKG?

Servers from other publishers that do the same job: Codebase Memory MCP server, Trace MCP server and Honcho MCP server. Compare all NVIDIA AI CKG alternatives.