io.github.Yarmoluk/ckg-nvidia-nemoclaw

Est-ce que io.github.Yarmoluk/ckg-nvidia-nemoclaw est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.Yarmoluk/ckg-nvidia-nemoclaw » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 8 outils

• ask_nemoclaw≈ 201 tokens

  Answer a question about NVIDIA NemoClaw by traversing the knowledge graph. Covers: agent runtimes (OpenClaw/Hermes/Deep Agents), OpenShell platform, inference routing, network policy, security layers, deployment paths, progressive tool disclosure, managed MCP servers, snapshots, shields, FOX Blueprint, Nemotron 3 Ultra ecosystem, and platform support. Args: question: Your question about NemoClaw concepts or architecture.

  Paramètres, retour & exemple (1)

  Paramètres

  • question · string · requis

  Exemple d'appel

  {"name": "ask_nemoclaw", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• get_prerequisites≈ 141 tokens

  Return the full upstream prerequisite chain for a NemoClaw concept. Useful for understanding what a concept depends on end-to-end. Args: concept: Exact or partial concept label.

  Paramètres, retour & exemple (1)

  Paramètres

  • concept · string · requis

  Exemple d'appel

  {"name": "get_prerequisites", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• list_domains≈ 82 tokens

  List available domains in this CKG server.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_domains", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• query_ckg≈ 153 tokens

  Return the typed subgraph around a NemoClaw concept. Args: concept: Exact or partial concept label (e.g. 'OpenClaw', 'NetworkPolicy', 'L7Proxy'). depth: Traversal hops (1–5, default 3).

  Paramètres, retour & exemple (2)

  Paramètres

  • depth · integer · optionnel
  • concept · string · requis

  Exemple d'appel

  {"name": "query_ckg", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• query_intersect≈ 524 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 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. 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.

  Paramètres, retour & exemple (5)

  Paramètres

  • mode · string · optionnel
  • depth · integer · optionnel
  • limit · integer · optionnel
  • branches · array · requis
  • direction · string · optionnel

  Exemple d'appel

  {"name": "query_intersect", "arguments": {"branches": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• route_query≈ 282 tokens

  Route a NemoClaw question to the optimal model and reasoning approach via graph depth. The CKG graph IS the router. NemoClaw's dependency chains (e.g. OpenShell → L7Proxy → CorporateCA → mTLS) are deep and typed — hop depth is a deterministic complexity signal. No heuristic: the graph decides which model and reasoning approach to use. Routing table: hop_depth 1 → haiku · direct (single concept lookup) hop_depth 2 → sonnet · generic_cot (moderate chain) hop_depth 3+ → opus · sparql_cot (deep chain, structured reasoning required) Args: question: Concept name or natural language question about NemoClaw / OpenShell. Returns: model_tier + reasoning_approach + why + context subgraph to inject before LLM call.

  Paramètres, retour & exemple (1)

  Paramètres

  • question · string · requis

  Exemple d'appel

  {"name": "route_query", "arguments": {"question": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• search_concepts≈ 126 tokens

  Fuzzy search for NemoClaw concepts by name or keyword. Args: query: Partial name or keyword (e.g. 'policy', 'inference', 'agent').

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · requis

  Exemple d'appel

  {"name": "search_concepts", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

• verify_source≈ 270 tokens

  Return the authoritative source URL and content hash for a NemoClaw concept node. Every node in the CKG was declared from a specific source document. This tool returns the source URL (where the node came from) and the SHA-256 hash of that document's bytes at extraction time. A hash mismatch on re-fetch means either the source has changed (stale edge — re-extract) or the graph was patched without re-fetching (silent edit — investigate). Audit chain: edge answer → graph commit → source_hash → source_url (fetch hint) Verification: curl -s <source_url> | sha256sum # compare output to source_hash Args: concept: Exact or partial concept label (e.g. 'CorporateCA', 'L7Proxy').

  Paramètres, retour & exemple (1)

  Paramètres

  • concept · string · requis

  Exemple d'appel

  {"name": "verify_source", "arguments": {"concept": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"result": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

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