NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 9 tools
Most tools have clearly distinct purposes: listing, searching, traversing, intersecting, routing, and verifying are all separated. The main potential confusion is between get_prerequisites and query_ckg, since both traverse prerequisite relationships, though the former is explicitly ordered and full-chain while the latter is general graph traversal.
All tool names follow a consistent verb_noun pattern: ask, get, list, query, route, search, verify. Even the query_* pair is consistent, and the one brand-tinged name (ask_nvidia) still follows the same verb_noun structure.
Nine tools is a well-scoped set for an NVIDIA knowledge-graph server. There are enough tools to cover discovery, querying, specialized traversal, routing, and verification without feeling bloated or thin.
The surface covers domain listing, concept search, graph traversal, prerequisite chains, conjunctive queries, routing, NL question answering, and source verification—strong coverage for a knowledge-graph query server. A minor gap is the lack of a direct get-concept-details tool, though query_ckg and ask_nvidia partially compensate.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
query_intersectget_prerequisites1 field changedOutput schema / (root)Previous value: -{
- "properties": {
- "result": {
- "title": "Result",
- "type": "string"
- }
- },
- "required": [
- "result"
- ],
- "title": "get_prerequisitesOutput",
- "type": "object"
-}New value: +nullquery_ckg1 field changedOutput schema / (root)Previous value: -{
- "properties": {
- "result": {
- "title": "Result",
- "type": "string"
- }
- },
- "required": [
- "result"
- ],
- "title": "query_ckgOutput",
- "type": "object"
-}New value: +nullask_nvidiaget_prerequisiteslist_domainslist_ecosystemquery_ckgroute_querysearch_conceptsverify_sourceNVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Art provenance intelligence — 282K-node knowledge graph with cited answers and honest gaps.
Graph-native persistent memory for AI agents — 33 MCP tools, zero-LLM writes.
Add one secure layer between your agents and this server.