NVIDIA AI CKG
io.github.Yarmoluk/ckg-nvidia-ai
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
— the operator's own registry description reported
Publisher io.github.Yarmoluk · first seen 2026-08-12 · endpoint https://ckg-nvidia-ai.onrender.com/mcp
Dependency rating derived
block — dead / unreachable · kind unknown · V n/a
Cluster not-mcp · distinctiveness —. Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.
🔏 Signed receipt rr_ecf593ebd3d7f9792c97552e · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.
● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →
History observed
Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.
changelog (2 events)
| date | type | what changed |
|---|---|---|
| 2026-08-14 | outcome | not_mcp (was ok_tools) |
| 2026-08-12 | outcome | first probe: ok_tools |
What kind of tools these are derived
Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from the operator's own registry description — REPORTED, not observed (tools were not visible to the probe). What checking applies to each kind (the full methodology →):
| nature | tools | meaning | what checking applies |
|---|---|---|---|
| unclassified | 1 | not classifiable from its text | Tier-1 only until its tools describe themselves |
Tools last seen observed
Truth checks observed
Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.
Drift observed
No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.
Looking for an alternative?
This server doesn't answer, but these live, allow-verdict servers describe themselves similarly — similar by what they say they do — never verified drop-in replacements; check each one before depending on it.
| server | verdict | shared terms |
|---|---|---|
| io.github.Yarmoluk/ckg-nvidia-nemoclaw NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native. | allow | 11x, domains, fewer, graphs |
| io.github.Hlobo-dev/tengu-firm One MCP key: prices, fundamentals, SEC filings, insider/13F/congressional trades. 336 tools. | allow | graphs, knowledge, nvidia |
| io.github.JcJamet/ia-qa-toolbox 130+ QA & dev tools for AI agents: prompt injection, RAG testing, VLM eval, guardrails. Free. | allow | fewer, knowledge, nvidia |
| io.github.CueCrux/vaultcrux-memory-core VaultCrux Memory Core — 32 tools: knowledge, decisions, constraints, signals, coverage | allow | domains, graphs, knowledge |
| io.github.Schoasch/backtesting-arena Crypto backtesting & Bitcoin cycle analytics. Point-in-time, DSR-corrected, look-ahead-aware. | allow | fewer, graphs, knowledge |
raw probe records
| probed (UTC) | outcome | http | ms | protocol |
|---|---|---|---|---|
| 2026-08-14T19:59:19Z | not_mcp | 200 | 205 | |
| 2026-08-12T05:34:32Z | ok_tools | 200 | 102 | 2025-06-18 |
Watch or embed this verdict
Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:
[](https://robinsaige.com/s/io.github.Yarmoluk/ckg-nvidia-ai)
Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.