Search / io.github.Yarmoluk/ckg-nvidia-nemoclaw
NVIDIA NemoClaw CKG
R0· no sign-inNVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
v0.10.3 · active · repository · descriptor JSON · versions
Search / io.github.Yarmoluk/ckg-nvidia-nemoclaw
R0· no sign-inNVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
v0.10.3 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"ckg-nvidia-nemoclaw": {
"type": "http",
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
}
}
}claude mcp add --transport http ckg-nvidia-nemoclaw https://ckg-nvidia-nemoclaw.onrender.com/mcp[mcp_servers.ckg-nvidia-nemoclaw]
url = "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"ckg-nvidia-nemoclaw": {
"type": "remote",
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp",
"enabled": true
}
}
}{
"mcpServers": {
"ckg-nvidia-nemoclaw": {
"type": "http",
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=ckg-nvidia-nemoclaw&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vY2tnLW52aWRpYS1uZW1vY2xhdy5vbnJlbmRlci5jb20vbWNwIn0%3D"
}{
"servers": {
"ckg-nvidia-nemoclaw": {
"type": "http",
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
}
}
}{
"mcpServers": {
"ckg-nvidia-nemoclaw": {
"httpUrl": "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
}
}
}extensions:
"ckg-nvidia-nemoclaw":
enabled: true
name: "ckg-nvidia-nemoclaw"
type: streamable_http
uri: "https://ckg-nvidia-nemoclaw.onrender.com/mcp"
timeout: 300
protocol.modernnewest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28protocol.statelessonly applies to 2026-07-28 serversprotocol.transportstreamable HTTPprotocol.list_ttlonly applies to 2026-07-28 serversauth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptionsevery tool has a descriptiontools.description_length1 tools have descriptions over 1,024 characters, which crowds the contexttools.schemasevery tool has an object input schematools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky onestools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: verify_source (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); query_ckg (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_concepts (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …tools.token_costabout 1,325 tokens to load every tooltools.api_dumptools are not a one-to-one API dumpstability.changes16 tool changes in 30 daysstability.rug_pullno tool changed its meaning under the same namedeps.known_vulnsno known advisory in 37 resolved packagesdeps.mcp_sdk_versionmcp 1.30.0, no known advisorydeps.resolvable[email protected] resolved: 37 packagesquery_intersectaddedAnswer 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.
route_queryaddedRoute 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.
verify_sourceaddedReturn 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').
list_domainsaddedList available domains in this CKG server.
search_conceptsaddedFuzzy search for NemoClaw concepts by name or keyword. Args: query: Partial name or keyword (e.g. 'policy', 'inference', 'agent').
get_prerequisitesaddedReturn 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.
query_ckgaddedReturn 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).
ask_nemoclawaddedAnswer 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.
list_domainsremovedList available domains in this CKG server.
query_intersectremovedAnswer 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.
Showing the latest 10. Full history: list_changes · trend: quality JSON.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +namespace-matches-repo +reachable +uptime-100% ~updated-82d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
[email protected] PyPI36 dependencies, resolved · MCP SDK mcp 1.30.0 · advisories checked 2026-10-19
No known advisory affects this dependency graph.
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| remote | auth | reachable | uptime 30d | p50 | protocol | last ok |
|---|---|---|---|---|---|---|
https://ckg-nvidia-nemoclaw.onrender.com/mcp streamable-http | none | yes | 100% | 283 ms | 2025-11-25 | 2026-10-19 |
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
ckg-nvidia-nemoclaw | pypi | 0.10.3 | uvx |
ask_nemoclaw | 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. |
get_prerequisites | 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. |
list_domains | List available domains in this CKG server. |
query_ckg | 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). |
query_intersect | 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. |
route_query | 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. |
search_concepts | Fuzzy search for NemoClaw concepts by name or keyword. Args: query: Partial name or keyword (e.g. 'policy', 'inference', 'agent'). |
verify_source | 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'). |
Schemas: list_tools.
{
"name": "io.github.Yarmoluk/ckg-nvidia-nemoclaw",
"title": "NVIDIA NemoClaw CKG",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://ckg-nvidia-nemoclaw.onrender.com/mcp",
"type": "streamable-http"
}
],
"version": "0.10.3",
"packages": [
{
"version": "0.10.3",
"transport": {
"type": "stdio"
},
"identifier": "ckg-nvidia-nemoclaw",
"runtimeHint": "uvx",
"registryType": "pypi"
}
],
"repository": {
"url": "https://github.com/Yarmoluk/ckg-nvidia-nemoclaw",
"source": "github"
},
"description": "NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native."
}