NVIDIA AI CKG
by ckg-nvidia-ai.onrender.com in Developer tools
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
https://ckg-nvidia-ai.onrender.com/mcp
Last 30 days
- Uptime
- 100%
- Response time
- 208 ms typical, 208 ms slowest 5%
- Last check
- 4 h ago
- Next check
- in 1 h
How to call it
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"nvidia-ai-ckg": {
"type": "http",
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}9 tools
- 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-i
- 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_OLLAM
- 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
- 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: Co
- 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
Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 4 h ago | Passed | 200 | 208 ms |
| 14 h ago | Passed | 200 | 452 ms |