NVIDIA AI CKG
Rank #2,783io.github.Yarmoluk/ckg-nvidia-ai
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
What you can do with NVIDIA AI CKG
NVIDIA AI CKG is a Model Context Protocol (MCP) server published by yarmoluk. It ranks #2,783 of 144,396 active servers on MCP Toplist, and its repository has 9 GitHub stars. NVIDIA AI CKG is listed across 3 registries — Official MCP, PulseMCP and mcp.so, with 5 tracked versions. It was first listed on Jul 7, 2026 and most recently updated on Jul 29, 2026.
Not verifiedMCP Toplist has not yet written a checked profile for this server, so the paragraph above is assembled from registry data only. The repository README is the authority on what it does.
What NVIDIA AI CKG can and cannot do
Not verifiedMCP Toplist has not catalogued this server's tools or limitations. The repository README lists them.
What you need before using NVIDIA AI CKG
The registry listing declares no required environment variables or authentication. This is declared metadata, not a verified install — the repository README is the authority.
MCP Toplist probed the public endpoint on Oct 14, 2026 and could not complete the MCP handshake (jsonrpc error). Requirements remain unverified.
Declared by the Official MCP Registry, last synced Oct 16, 2026. Not independently verified by MCP Toplist.
Hosted endpoint declared as public.
Connect NVIDIA AI CKG and confirm it works
claude mcp add --transport http ckg-nvidia-ai https://ckg-nvidia-ai.onrender.com/mcpclaude mcp add ckg-nvidia-ai -- uvx ckg-nvidia-ai[mcp_servers.ckg-nvidia-ai]
url = "https://ckg-nvidia-ai.onrender.com/mcp"Add to ~/.codex/config.toml.
[mcp_servers.ckg-nvidia-ai]
command = "uvx"
args = ["ckg-nvidia-ai"]Add to ~/.codex/config.toml.
https://ckg-nvidia-ai.onrender.com/mcpSettings → Connectors → “Add custom connector”, then paste this URL.
{
"mcpServers": {
"ckg-nvidia-ai": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}Add to claude_desktop_config.json (Settings → Developer → Edit Config).
{
"mcpServers": {
"ckg-nvidia-ai": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project).
{
"mcpServers": {
"ckg-nvidia-ai": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (per project).
{
"servers": {
"ckg-nvidia-ai": {
"type": "http",
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}Save as .vscode/mcp.json in your workspace.
{
"servers": {
"ckg-nvidia-ai": {
"type": "stdio",
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}Save as .vscode/mcp.json in your workspace.
{
"mcpServers": {
"ckg-nvidia-ai": {
"serverUrl": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
{
"mcpServers": {
"ckg-nvidia-ai": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
{
"mcpServers": {
"ckg-nvidia-ai": {
"url": "https://ckg-nvidia-ai.onrender.com/mcp"
}
}
}{
"mcpServers": {
"ckg-nvidia-ai": {
"command": "uvx",
"args": [
"ckg-nvidia-ai"
]
}
}
}After adding the config, ask your client to list this server's tools. A tool list confirms the connection; an empty list or an error means the server did not start or needs credentials.
When to choose another server
- CKG-MCP — Compressed Knowledge Graphs#4,827
- NVIDIA NemoClaw CKG#6,260
- Salesforce AgentForce CKG#9,484
- ckg-nemotron-perplexity#22,438
- agent-memory-mcp#125,561
No task-specific alternatives are catalogued for NVIDIA AI CKGyet; the list above is its publisher's other servers.
What changed, and when this was checked
- First listed
- Jul 7, 2026
- Latest version published
- Jul 29, 2026
- Version history
- 5 versions tracked (below)
- Requirements evidence
- MCP Toplist probed the public endpoint on Oct 14, 2026 and could not complete the MCP handshake (jsonrpc error). Requirements remain unverified.
- Profile checked
- Not yet — purpose, capabilities and requirements above come from registry data only
- Ranking data as of
- Oct 16, 2026
- PulseMCP ↗listed since Jul 10, 2026 · still listed
- Official MCP ↗listed since Jul 24, 2026 · still listed
- mcp.so ↗listed since Aug 25, 2026 · still listed
Do you maintain NVIDIA AI CKG? to correct or enrich this profile.
Available versions (5)
| Version | Published |
|---|---|
| 0.16.4 | Jul 29, 2026 |
| 0.7.1 | Jul 22, 2026 |
| 0.5.3 | Jul 8, 2026 |
| 0.5.2 | Jul 8, 2026 |
| 0.3.2 | Jul 7, 2026 |
Ranks ahead of 141,613 of 144,396 servers on MCP Toplist.
Show your rank
Maintain this server? Add the live rank badge to your README — it updates automatically as the leaderboard changes.
[](https://mcptoplist.com/server/io.github.Yarmoluk%2Fckg-nvidia-ai)<a href="https://mcptoplist.com/server/io.github.Yarmoluk%2Fckg-nvidia-ai"><img src="https://mcptoplist.com/badge/io.github.Yarmoluk%2Fckg-nvidia-ai.svg" alt="MCP Toplist: Top 5% of 144,396" /></a>Variants: append ?metric=score or ?metric=stars to the image URL.
Frequently asked questions
- Who maintains NVIDIA AI CKG?
- NVIDIA AI CKG is maintained by yarmoluk, which publishes 6 MCP servers (17 total versions) tracked on MCP Toplist.
- Is NVIDIA AI CKG listed on the Official MCP Registry?
- Yes — NVIDIA AI CKG is listed on the Official MCP Registry, alongside PulseMCP and mcp.so.
- How many versions does NVIDIA AI CKG have?
- MCP Toplist tracks 5 versions of NVIDIA AI CKG, most recently published on Jul 29, 2026.
- Where can I find the source code for NVIDIA AI CKG?
- The source code for NVIDIA AI CKG is hosted at github.com/yarmoluk/ckg-nvidia-ai.
Do you run this server?
Community projects list the MCP servers behind real agents and apps. Publish yours and this page will link to it.