mcp server
NVIDIA NemoClaw CKG
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Description as published by the maintainer. Source
- version 0.10.3
- active
- retrieval
- memory and context
active — Registry entry last updated 2026-07-29. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
8 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
ask_nemoclaw(question)- 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. Required: question.
get_prerequisites(concept)- 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. Required: concept.
list_domains- List available domains in this CKG server.
query_ckg(depth, concept)- 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). Required: concept.
query_intersect(mode, depth, limit, branches, direction)- 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. Required: branches.
route_query(question)- 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. Required: question.
search_concepts(query)- Fuzzy search for NemoClaw concepts by name or keyword. Args: query: Partial name or keyword (e.g. 'policy', 'inference', 'agent'). Required: query.
verify_source(concept)- 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'). Required: concept.
Last successful function declaration observed on . Source: https://ckg-nvidia-nemoclaw.onrender.com/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://ckg-nvidia-nemoclaw.onrender.com/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 0.10.3 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-29 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-29 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| mcp tools declared | 8 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | ckg-nvidia-nemoclaw.onrender.com | |
| mcp endpoint status | ok | The server listed 8 functions when asked. | as of probe | ckg-nvidia-nemoclaw.onrender.com |
Where to get it
Also from yarmoluk
-
Salesforce AgentForce CKG
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
-
io.github.Yarmoluk/ckg-mcp
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
-
io.github.Yarmoluk/ckg-nemotron-perplexity
NVIDIA Nemotron + Perplexity Sonar as knowledge graphs — 2 domains, 83 nodes. MCP-native.
-
NVIDIA AI CKG
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json