Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

NVIDIA NemoClaw CKG

PYPI · CKG-NVIDIA-NEMOCLAW · 2 COMPONENTS

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

−15 this week 60 Trust /100

Last scanned (11 hours ago)

Scores higher than 53% of PyPI servers

Category AI and Machine Learning

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security44
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Declares code that runs automatically (build-time code we could not rule out (a Hatch, PDM or setuptools build hook, a dynamic version we could not read statically, shipped VCS metadata or a stray root module)) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does. View diagnostics → Partial
  • 0 of 28 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 28 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability73
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 759 tokens (~108/item across 7 items; 7 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
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 (100% 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 7 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 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
What we tested

Checks we ran (14)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (2)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.
  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

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.

  • 21 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
  • 18 Nov 26 +14
    • Malware scan: unverified → pass ▲ security
    • Stability: pass → 0.97 functional
  • 17 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 12 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
    • Stability: 0.97 → pass security
  • 11 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 8 Nov 26 −2
    • Stability: pass → 0.87 functional
Diagnostics

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 21 Nov 2026 · Analysed pypi/ckg-nvidia-nemoclaw@0.10.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Install scripts 2 scripts
Hook Tier Command
build_backend Known build tool hatchling.build
build_hook Not reviewed hatch_build.py,tool.hatch.build.hooks.custom

Background: Why install scripts are a supply-chain risk →

Dependencies 28 packages
Packages resolved 28
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 7 exposed · ~684 tokens

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 →

Tool Tokens
ask_nemoclaw ~108

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.

NameTypeReqDescription
questionstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

get_prerequisites ~53

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.

NameTypeReqDescription
conceptstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

list_domains ~17

List available domains in this CKG server.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes–

No examples provided.

query_ckg ~78

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).

NameTypeReqDescription
conceptstringyes–
depthinteger––
NameTypeReqDescription
resultstringyes–

No examples provided.

route_query ~196

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.

NameTypeReqDescription
questionstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

search_concepts ~53

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

NameTypeReqDescription
querystringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

verify_source ~179

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').

NameTypeReqDescription
conceptstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

Install

How do I install the NVIDIA NemoClaw CKG MCP server?

NVIDIA NemoClaw CKG runs locally as a PyPI package, launched with uvx ckg-nvidia-nemoclaw. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · ckg-nvidia-nemoclaw

# add to Claude Code
claude mcp add yarmoluk-ckg-nvidia-nemoclaw -- uvx ckg-nvidia-nemoclaw
Common questions

What is the NVIDIA NemoClaw CKG MCP server?

NVIDIA NemoClaw CKG is an MCP server listed in the public MCP registry as io.github.Yarmoluk/ckg-nvidia-nemoclaw. NVIDIA NemoClaw knowledge graph, 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native. This page covers its PyPI package (ckg-nvidia-nemoclaw).

Is the NVIDIA NemoClaw CKG MCP server safe to use?

NVIDIA NemoClaw CKG scores 60 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. 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 NemoClaw CKG MCP server expose?

NVIDIA NemoClaw CKG exposes 7 tools: ask_nemoclaw, query_ckg, get_prerequisites, search_concepts, list_domains, and 2 more. Their descriptions and schemas cost roughly 684 tokens of context every time the server is loaded.

Is the NVIDIA NemoClaw CKG MCP server still maintained?

NVIDIA NemoClaw CKG is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the NVIDIA NemoClaw CKG MCP server under?

NVIDIA NemoClaw CKG declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the NVIDIA NemoClaw CKG MCP server?

VerifyMCP ran 14 checks on NVIDIA NemoClaw CKG, covering Known CVEs, Install scripts, Dependency health, Source repository and 10 more. 2 items could not be completed, a gap on our side rather than a finding about NVIDIA NemoClaw CKG: Malware scan and Security disclosure. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.