MCP server

NVIDIA AI CKG

io.github.Yarmoluk/ckg-nvidia-ai

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

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

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

9

Token cost

About 1,895 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.ckg-nvidia-ai]
url = "https://ckg-nvidia-ai.onrender.com/mcp"

Gemini CLI

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

Cursor

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

VS Code

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

Antigravity

agy mcp add ckg-nvidia-ai https://ckg-nvidia-ai.onrender.com/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"ckg-nvidia-ai","server_url":"https://ckg-nvidia-ai.onrender.com/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"ckg-nvidia-ai","server_url":"https://ckg-nvidia-ai.onrender.com/mcp"}

Tools

• ask_nvidia ~216 tokens
  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:
• get_prerequisites ~144 tokens
  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 ~53 tokens
  List all 20 NVIDIA AI domains available in this knowledge graph.
• list_ecosystem ~61 tokens
  Discover other CKG packages for adjacent domains — finance, healthcare, legal, and more.
• query_ckg ~183 tokens
  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
• query_intersect ~591 tokens
  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
• route_query ~316 tokens
  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
• search_concepts ~140 tokens
  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 ~191 tokens
  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

Browse

• GitHub tools
• Domains and DNS
• Legal research
• GitHub and code hosting
• Running code

Related MCP servers

• NVIDIA NemoClaw CKG
  NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
• Salesforce AgentForce CKG
  Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
• Brainkb
  MCP server for querying BrainKB, a knowledge base for neuroscience knowledge graphs.
• ZenithEye Agent Commons
  Public coordination substrate for AI systems and humans with bounded MCP discovery and creation.
• Precision-concretecoating
  Precision Concrete Coating MCP for services, estimates, scheduling, and business information.
• NightWatch Live Intelligence
  Real-time crypto asset intel for trading AIs: liquidity grades, transfer routes, spreads, BTI
• AuditAE SEO MCP
  SEO MCP: Search Console, GA4, SERP and domain data, rank tracking, AI citations and site fixes.
• Backtesting Arena
  Crypto backtesting & Bitcoin cycle analytics. Point-in-time, DSR-corrected, look-ahead-aware.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.Yarmoluk/ckg-nvidia-ai.svg)](https://aptlynx.net/servers/io.github.Yarmoluk/ckg-nvidia-ai)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents