Skip to content
MCP server

NVIDIA AI CKG

NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance…

Install
Pricing
Open source
Runs
Locally or Remotely
Version
0.16.4
Listing updated
5 days ago

About NVIDIA AI CKG

NVIDIA AI CKG is an open-source MCP server. It can run locally on your machine or as a hosted remote server.

NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.

Install

Run in a terminal

claude mcp add --transport http ckg-nvidia-ai https://ckg-nvidia-ai.onrender.com/mcp

Add to Settings → Connectors → Add custom connector

https://ckg-nvidia-ai.onrender.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "ckg-nvidia-ai": {
      "url": "https://ckg-nvidia-ai.onrender.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "ckg-nvidia-ai": {
      "type": "http",
      "url": "https://ckg-nvidia-ai.onrender.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ckg-nvidia-ai": {
      "serverUrl": "https://ckg-nvidia-ai.onrender.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "ckg-nvidia-ai": {
      "type": "http",
      "url": "https://ckg-nvidia-ai.onrender.com/mcp"
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Pricing

Open source

NVIDIA AI CKG FAQ

Is NVIDIA AI CKG free?

Yes. NVIDIA AI CKG is open source, so you can use and self-host it for free.

How do I add NVIDIA AI CKG to Claude Code?

Run this command in your terminal: claude mcp add --transport http ckg-nvidia-ai https://ckg-nvidia-ai.onrender.com/mcp

Where this comes from

  • Description: from the official MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers