Skip to content
External endpointresponds

NVIDIA NemoClaw CKG

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

Endpoint URL
https://ckg-nvidia-nemoclaw.onrender.com/mcp
Current status
responds
Last checked
Aug 17, 2026, 05:00 AM UTC
Check
MCP initialize · 8s limit
Latency
152 ms
Response record
4 of 4 rounds
Transport
streamable-http
Source
mcp_registry
Registry name
io.github.Yarmoluk/ckg-nvidia-nemoclaw

Current observation

This endpoint answered at its latest recorded check.

What this server reports about itself

Self-reported at initialize. Not verified by Licium.

Server name
ckg-nvidia-nemoclaw
Version
1.29.0
Capability keys
experimental, prompts, resources, tools
Tool names
ask_nemoclaw, query_ckg, get_prerequisites, search_concepts, list_domains, verify_source, route_query, query_intersect
Instructions excerpt

NVIDIA NemoClaw CKG — 55 nodes, 74 edges covering sandboxed AI agent infrastructure. Workflow: search_concepts(query) to resolve a concept, then query_ckg(concept) for its typed subgraph or get_prerequisites(concept) for the full upstream chain. Every result traces to a declared edge — no probabilistic inference.

Reported Aug 17, 2026, 05:00 AM UTC.

Check history

Oldest to newest. Each row is one recorded check.

  1. responds
    MCP initialize · 8s limit · HTTP 200 · 194ms
  2. responds
    MCP initialize · 8s limit · HTTP 200 · 329ms
  3. responds
    MCP initialize · 8s limit · HTTP 200 · 248ms
  4. responds
    MCP initialize · 8s limit · HTTP 200 · 152ms