NVIDIA AI CKG MCP Server

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

People connecting memory tools to Claude, Cursor, VS Code, or another MCP client.

REPOSITORY REMOVED

LAST COMMIT unknown · VERIFIED 2026-08-25

how we verify → /methodology

01 · Install NVIDIA AI CKG

Claude Code

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

Claude Desktop / Cursor / VS Code - add to config

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

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://ckg-nvidia-ai.onrender.com/mcp

transport: streamable-http

endpoint alive - responded to MCP initialize · probed 2026-08-25

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · remote - your agent's requests go to ckg-nvidia-ai.onrender.com

endpoint auth accepted our unauthenticated MCP initialize - no credentials needed to connect

license no standard license detected - usage rights unclear; check the repo before commercial use

pypi package ckg-nvidia-ai - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.Yarmoluk is GitHub-verified and matches the repo owner

03 · Who maintains NVIDIA AI CKG

NVIDIA AI CKG is maintained by yarmoluk. We track 5 MCP servers from yarmoluk - 0 actively maintained, 0 combined GitHub stars.

04 · Facts

repository: github.com/yarmoluk/ckg-nvidia-ai
category: memory - vanished as of 2026-08-25.
registry: io.github.Yarmoluk/ckg-nvidia-ai (active, first published 2026-07-07 · 5 versions)
packages: pypi:ckg-nvidia-ai

05 · NVIDIA AI CKG FAQ

What is NVIDIA AI CKG?

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

Is NVIDIA AI CKG still maintained?

Its last commit was unknown (as of 2026-08-25) - we classify it as vanished.

How do I install NVIDIA AI CKG?

Run `uvx ckg-nvidia-ai`. You can also paste the ready-made client config above.

Does NVIDIA AI CKG require authentication?

No - the endpoint accepted our unauthenticated MCP initialize when probed on 2026-08-25; you can connect without credentials.

06 · Alternatives to NVIDIA AI CKG

Alternatives to NVIDIA AI CKG

Maintained memory servers if NVIDIA AI CKG isn't the fit.

Pairs well with

Servers that cover what NVIDIA AI CKG doesn't - only shown when the pairing reason fits the companion.