NVIDIA AI CKG
REMOTE · CKG-NVIDIA-AI.ONRENDER.COM · 2 COMPONENTS
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
Available components
Last scanned (21 hours ago)
Scores higher than 53% of remote servers
Reachable. Last reached 4 Nov 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability80
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 1495 tokens (~149/item across 10 items; 9 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (67% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 +45
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Stability: unverified → 0.33 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- 26 Oct 26 −40
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: 0.03 → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
- Schema quality: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- 25 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 24 Oct 26 +40
- Injection markers: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 12 Sept 26 0
- Endpoint reachability: reachable → not serving MCP ▼ security
- Tool safety: pass → unverified ▼ security
- Stability: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
- Tool coverage: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- 10 Sept 26 0
- Injection markers: unverified → pass ▲ security
- Stability: unverified → pass ▲ security
- Transport: fail → pass ▲ security
- Authorization: Authorisation not fully verified: no authorisation is required to call this server, and 9 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. security
- Endpoint reachability: not serving MCP → reachable ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Server version: 1.29.1 → 1.30.0 functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://ckg-nvidia-ai.onrender.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=onrender.com | CN=WE1,O=Google Trust Services,C=US | 21 Sept 2026 | 20 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | 6eb1e3fe7d0631ea1337bfa4a321c137 |
| SANs: onrender.com, *.onrender.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of ckg-nvidia-ai.onrender.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| onrender.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://ckg-nvidia-ai.onrender.com/mcp | Verified | 200 | |
| http (plaintext) | http://ckg-nvidia-ai.onrender.com/mcp | HTTPS enforced | 301 | https://ckg-nvidia-ai.onrender.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
ask_nvidia ~146
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: http://localhost:11434) Args: question: Natural-language question about the NVIDIA AI stack. domain: Domain from list_domains() — auto-detected from question if omitted.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | – |
| question | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
get_prerequisites ~79
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().
| Name | Type | Req | Description |
|---|---|---|---|
| concept | string | yes | – |
| domain | string | yes | – |
No output schema declared.
No examples provided.
list_domains ~21
List all 20 NVIDIA AI domains available in this knowledge graph.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
list_ecosystem ~28
Discover other CKG packages for adjacent domains — finance, healthcare, legal, and more.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
query_ckg ~122
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: Traversal depth 1–5 (default 3).
| Name | Type | Req | Description |
|---|---|---|---|
| concept | string | yes | – |
| depth | integer | – | – |
| domain | string | yes | – |
No output schema declared.
No examples provided.
query_intersect ~390
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 alone answers it; the answer lives in the overlap. Every branch is an exact set of declared edges, so the intersection is exact. A concept appears only if a declared path reaches it from each anchor. A relation missing from the graph produces an empty result, never a guess. Args: branches: Two or more branches. Either a bare anchor ("TensorRT-LLM"), which takes everything within `depth` hops, or an anchor plus an explicit relation path using '>' ("TensorRT-LLM > REQUIRES > ENABLES"), where each relation replaces the frontier. '*' matches any relation. Mix both forms freely. domain: Domain name from list_domains(). depth: Hops for bare-anchor branches, 1-5 (default 2). Ignored for explicit paths. direction: 'out' follows dependencies, 'in' follows them backwards, 'both' (default). mode: 'AND' (default) intersects branches; 'OR' unions them. limit: Max concepts listed, 1-200 (default 40). The true count is always shown. Returns: Markdown with the query plan and its per-step set sizes, then the answer set with taxonomy tags. Reports which branch was empty when the intersection is empty.
| Name | Type | Req | Description |
|---|---|---|---|
| branches | array | yes | – |
| depth | integer | – | – |
| direction | string | – | – |
| domain | string | yes | – |
| limit | integer | – | – |
| mode | string | – | – |
No output schema declared.
No examples provided.
route_query ~223
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 graph decides. Routing table: hop_depth 1 → haiku · direct (simple lookup) hop_depth 2 → sonnet · generic_cot (moderate chain) hop_depth 3+ → opus · sparql_cot (deep dependency, structured reasoning) Args: question: Concept name or natural language question about NVIDIA AI. domain: Domain from list_domains() — e.g. "nvidia-tensorrt-triton", "nvidia-nim". Returns: model_tier + reasoning_approach + why + context subgraph to inject before LLM call.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | – | – |
| question | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
search_concepts ~88
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'.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | – |
| query | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
verify_source ~123
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 match supported). domain: Domain from list_domains() — e.g. 'nvidia-nim', 'nvidia-tensorrt-triton'.
| Name | Type | Req | Description |
|---|---|---|---|
| concept | string | yes | – |
| domain | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the NVIDIA AI CKG MCP server?
NVIDIA AI CKG is a hosted endpoint at https://ckg-nvidia-ai.onrender.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · ckg-nvidia-ai.onrender.com
claude mcp add --transport http yarmoluk-ckg-nvidia-ai 'https://ckg-nvidia-ai.onrender.com/mcp'
What is the NVIDIA AI CKG MCP server?
NVIDIA AI CKG is an MCP server listed in the public MCP registry as io.github.Yarmoluk/ckg-nvidia-ai. NVIDIA AI knowledge graphs, 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native. This page covers its hosted endpoint (https://ckg-nvidia-ai.onrender.com/mcp).
Is the NVIDIA AI CKG MCP server safe to use?
NVIDIA AI CKG scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the NVIDIA AI CKG MCP server expose?
NVIDIA AI CKG exposes 9 tools: list_domains, search_concepts, query_ckg, get_prerequisites, ask_nvidia, and 4 more. Their descriptions and schemas cost roughly 1,220 tokens of context every time the server is loaded.
Does the NVIDIA AI CKG MCP server require authentication?
No. We connected to NVIDIA AI CKG without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the NVIDIA AI CKG MCP server still maintained?
NVIDIA AI CKG is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.