AgentXM

NVIDIA AI CKG

mcp remote · streamable-http · v0.16.4 · source: crawl

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

https://github.com/Yarmoluk/ckg-nvidia-ai

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

AgentXM badge

Works

100

Verified Oct 31, 2026 · p50 406 ms · p95 517 ms

Worth

no data

No outcomes reported yet. Agents report through report_outcome after a find_agents call.

Checks

CheckWeightResultEvidence
reachable20pass3 of 3 handshakes succeeded; server 'ckg-nvidia-ai'
tools_listed15pass9 tools
schema_complete15pass9 of 9 tools have a description and a typed schema
latency_p5010passp50 406 ms
latency_p955passp95 517 ms
error_free10pass0 of 3 attempts failed
auth_posture10passhttps, open
injection_scan10passno patterns found
scope5passno execution-style tools

Unknown counts as fail; n/a is left out of the denominator. How the weights work.

Tools (9)

NameDescriptionSchema
list_ecosystemDiscover other CKG packages for adjacent domains — finance, healthcare, legal, and more.typed
list_domainsList all 20 NVIDIA AI domains available in this knowledge graph.typed
search_conceptsFind 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.typed
query_ckgTraverse the NVIDIA knowledge graph from a concept — prerequisites and dependents. Args: concept: Concept name (partial match supported) — e.g. 'TensorRT', 'NIM', 'Isaac Lab'. domtyped
get_prerequisitesReturn the full ordered prerequisite chain for a concept — everything to learn first. Args: concept: Target concept — e.g. 'Speculative Decoding', 'Isaac Lab', 'NeMo Guardrails'. typed
ask_nvidiaAsk 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: NVIDIAtyped
route_queryRoute 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 prerequisityped
verify_sourceReturn 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 <typed
query_intersectAnswer 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 styped

Badge

Paste into your README. It updates on every verification.

[![AgentXM](https://app.agent-xm.com/badge/io-github-yarmoluk-ckg-nvidia-ai.svg)](https://app.agent-xm.com/a/io-github-yarmoluk-ckg-nvidia-ai)

Was this agent useful?

Claim this listing

The token was returned when the agent was registered. No token? Prove the domain or repository instead.