What are the prerequisites to run this server?
Go 1.20+, Make, npm, kubectl, access to a Kubernetes cluster, and a valid `kubeconfig.yaml` file with appropriate permissions.
@linode
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"capi-mcp": {
"command": "/absolute/path/to/capi-mcp/bin/capi-mcp",
"env": {
"KUBECONFIG": "/absolute/path/to/your/kubeconfig.yaml"
}
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
capi-mcp is a tool that integrates Cluster API (CAPI) resources with the Model Context Protocol (MCP), enabling programmatic and prompt-based management of Kubernetes clusters and machines. It is designed for Kubernetes operators and developers who manage clusters declaratively using CAPI.
Build the binary with make build (requires Go, Make, npm, kubectl, and a valid kubeconfig). Run the MCP inspector for testing: npx @modelcontextprotocol/inspector -e KUBECONFIG=kubeconfig.yaml bin/capi-mcp. For use with Claude Desktop or VSCode, add the server configuration to the respective MCP settings file, specifying the absolute path to the binary and the KUBECONFIG environment variable.
Go 1.20+, Make, npm, kubectl, access to a Kubernetes cluster, and a valid `kubeconfig.yaml` file with appropriate permissions.
Clone the repository and run `make build` to compile the binary.
Configure the server in Claude Desktop’s configuration file (`claude_desktop_config.json`) by adding the absolute path to the binary and setting the `KUBECONFIG` environment variable.
Tools include `list_clusters`, `get_cluster`, `get_cluster_kubeconfig`, `check_upgrade

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Free enterprise-grade due diligence for the app you built, run by your own coding agent: 118 read-only checks plus an 18-dimension review, scored 1-5 with file-and-line evidence and a report page behind an access code. N

Read-only Total CMS docs and site content over MCP: exact Twig signatures, field types, schema options, the CLI, release notes and comparisons. No key required.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
コメント