NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
Setup
Choose your client, copy the config, then fill in any required environment variables.
Local
claude mcp add nvidia-ai-ckg -- uvx ckg-nvidia-ai~/.codex/config.toml
[mcp_servers.nvidia-ai-ckg]
command = "uvx"
args = ["ckg-nvidia-ai"]
# codex mcp add nvidia-ai-ckg -- uvx ckg-nvidia-ai~/.cursor/mcp.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}.vscode/mcp.json
{
"servers": {
"nvidia-ai-ckg": {
"type": "stdio",
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}Remote
claude mcp add --transport http nvidia-ai-ckg https://ckg-nvidia-ai.onrender.com/mcp~/.codex/config.toml
[mcp_servers.nvidia-ai-ckg]
url = "https://ckg-nvidia-ai.onrender.com/mcp"
# codex mcp add nvidia-ai-ckg --url https://ckg-nvidia-ai.onrender.com/mcp~/.cursor/mcp.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"nvidia-ai-ckg": {
"type": "http",
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"httpUrl": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"nvidia-ai-ckg": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://ckg-nvidia-ai.onrender.com/mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"nvidia-ai-ckg": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}