NVIDIA AI CKG is a remote MCP server that gives an AI agent 9 tools, among them ask_nvidia, get_prerequisites, list_domains. It answers at https://ckg-nvidia-ai.onrender.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 21 October 2026, succeeded.
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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: NV Inputs: question, domain |
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(). Inputs: concept, domain |
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- Inputs: concept, domain, depth |
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 Inputs: branches, domain, depth, direction, mode, limit |
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) Inputs: question, domain |
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'. Inputs: query, domain |
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 Inputs: concept, domain |
Every block below points at https://ckg-nvidia-ai.onrender.com/mcp. Pick your client and copy.
claude mcp add --transport http nvidia-ai-ckg https://ckg-nvidia-ai.onrender.com/mcp
{
"mcpServers": {
"nvidia-ai-ckg": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://ckg-nvidia-ai.onrender.com/mcp"]
}
}
}{
"mcpServers": {
"nvidia-ai-ckg": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"servers": {
"nvidia-ai-ckg": {
"type": "http",
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"context_servers": {
"nvidia-ai-ckg": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"mcpServers": {
"nvidia-ai-ckg": {
"serverUrl": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"mcpServers": {
"nvidia-ai-ckg": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}name: NVIDIA AI CKG
version: 0.0.1
schema: v1
mcpServers:
- name: NVIDIA AI CKG
type: streamable-http
url: https://ckg-nvidia-ai.onrender.com/mcp{
"mcpServers": {
"nvidia-ai-ckg": {
"httpUrl": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"mcpServers": {
"nvidia-ai-ckg": {
"type": "http",
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"mcpServers": {
"nvidia-ai-ckg": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fckg-nvidia-ai.onrender.com%2Fmcp&type=streamable_http&id=nvidia-ai-ckg&name=NVIDIA%20AI%20CKG
It answered our last check on 21 October 2026 in 189 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
9, as returned by the server's own tools/list on 13 September 2026: ask_nvidia, get_prerequisites, list_domains, list_ecosystem, query_ckg, query_intersect, route_query, search_concepts, and 1 more.
It answered our last check on 21 October 2026 in 189 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://ckg-nvidia-ai.onrender.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
No: the publisher declares paid use. {"protocols": ["x402"], "price": 0.005, "currency": "USDC", "networks": ["base"], "verified": "live", "priceSource": "live", "checked": 1792574325}
Publisher: io.github.yarmoluk. Endpoint host: ckg-nvidia-ai.onrender.com. ARD identifier: urn:air:io.github.yarmoluk:mcp:ckg-nvidia-ai.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.