# NVIDIA NemoClaw CKG MCP server

NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-yarmoluk-ckg-nvidia-nemoclaw
- Repository: https://github.com/Yarmoluk/ckg-nvidia-nemoclaw

## Install
- Command: `uvx ckg-nvidia-nemoclaw`
- Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- Auth: Not captured

## Setup notes
- Package: Pypi ckg-nvidia-nemoclaw v0.10.3
- Remote endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp

## Tools
- 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.
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- 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).
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- 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.
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- search_concepts - Fuzzy search for NemoClaw concepts by name or keyword.

Args:
    query: Partial name or keyword (e.g. 'policy', 'inference', 'agent').
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- list_domains - List available domains in this CKG server. Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- 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').
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- 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.
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp
- 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.
 Endpoint: https://ckg-nvidia-nemoclaw.onrender.com/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.Yarmoluk
- Version: 0.10.3
- Runtime: Pypi
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 29, 2026
- Source: https://registry.modelcontextprotocol.io