pulsemcp verified Safe content atomic mcp-remote

Kubernetes GPU Agent

An ephemeral diagnostic agent for Kubernetes clusters that provides real-time NVIDIA GPU hardware introspection via stdio transport, designed for AI-assisted troubleshooting by SREs debugging complex hardware failures. Uses NVIDIA NVML library to expose GPU inventory, health monitoring, and XID error analysis tools through kubectl debug sessions, eliminating the need for persistent DaemonSets or standing infrastructure. Operates in read-only mode by default with an optional operator mode for destructive operations, featuring graceful degradation when GPU hardware is unavailable.

Cognium trust score

88%

Tier

Verified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.

Scan details: Circle-IR · 2026-09-28 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: cloud-infra
Source: PulseMCP
Repository: github.com/arangogutierrez/k8s-gpu-mcp-server
Author type: human
Last scanned: 2026-09-28
Updated: 2026-09-28

View source Find related skills

MCP

Resolve Kubernetes GPU Agent from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"