NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
NVIDIA AI CKG is an MCP integration. NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
The registry lists a streamable-http connection at https://ckg-nvidia-ai.onrender.com/mcp.
The published pypi package is ckg-nvidia-ai, version 0.16.4. Its declared MCP transport is stdio.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 0.16.4 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related knowledge & memory MCP servers for tools that cover the same kind of work.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
An MCP server that streams real-time cryptocurrency liquidation events from Binance.
Rag Knowledge Graph automation via MCP. Includes index document, rag query, add graph edge. ...
Register Knowerage wherever your MCP host expects server definitions (for example some clients use `.cursor/mcp.json` or `.vscode/mcp.json`; others
Agentic Retrieval Augmented Generation (RAG) with LanceDB