pulsemcp verified Safe content atomic mcp-remote

Cluster API

This MCP server provides a secure bridge between AI agents and Kubernetes Cluster API (CAPI) management clusters, enabling programmatic creation, scaling, and management of Kubernetes clusters across cloud providers through seven specialized tools including cluster lifecycle operations, node management, and kubeconfig retrieval. Built by jsell-rh using Go with comprehensive security controls, provider abstraction, and asynchronous operation handling, it translates high-level MCP tool calls into declarative Kubernetes API operations while monitoring cluster status until completion. The implementation features AWS provider support with extensible provider interface, robust authentication and input validation, structured error handling with sanitized client responses, and comprehensive observability through Prometheus metrics and structured logging, making it valuable for AI-assisted infrastructure automation, multi-cloud cluster management workflows, and building AI tools that need programmatic access to enterprise Kubernetes infrastructure without manual cluster management interfaces.

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/jsell-rh/capi-mcp
Author type: human
Last scanned: 2026-09-28
Updated: 2026-09-28

View source Find related skills

MCP

Resolve Cluster API 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"