What prerequisites are needed to run this server?
A Kubernetes cluster with Rook Ceph operator installed, kubectl configured with cluster access, and Node.js 18+ with npm.
@shreyanshjain7174
基本情報
A Model Context Protocol (MCP) server for managing Rook Ceph storage clusters in Kubernetes environments.
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": {
"rook-ceph-mcp": {
"command": "docker",
"args": [
"run",
"-p",
"3000:3000",
"rook-ceph-mcp"
]
}
}
}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。
Rook Ceph Mcp is a Model Context Protocol (MCP) server for managing Rook Ceph storage clusters in Kubernetes environments. It provides tools to list and monitor clusters, manage block pools, filesystems, and object stores, and offers pre-configured YAML templates and troubleshooting prompts.
Install dependencies with npm install, build with npm run build, then start in stdio mode (npm run start:stdio) or HTTP mode (npm start). A Docker image can be built and run. The server requires a Kubernetes cluster with Rook Ceph installed and uses the default kubeconfig for authentication. Example invocations include list_clusters, create_block_pool, and get_cluster_status.
A Kubernetes cluster with Rook Ceph operator installed, kubectl configured with cluster access, and Node.js 18+ with npm.
The server supports both stdio transport (for local development) and HTTP transport (for cloud hosting). In HTTP mode it exposes endpoints such as `/health`, `/mcp/tools`, and `/mcp/call-tool`.
Cluster operations include `list_clusters` and `get_cluster_status`. Storage resource tools include `list_block_pools`, `list_filesystems`, `list_object_stores`, `create_block_pool`, and `delete_resource`.
The server provides resources at URIs like `rook-ceph://manifests/cluster`, `rook-ceph://manifests/block-pool`, `rook-ceph://manifests/filesystem`, and `rook-ceph://manifests/object-store`.

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Hindsight: Agent Memory That Learns

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
A curated list of references for MLOps

Model Context Protocol Servers
コメント