What are the prerequisites for using KubeSphere MCP Server?
You must have a running KubeSphere cluster and know its access address, a valid username, and password.
KubeSphere MCP Server
@kubesphere
基本情報
KubeSphere MCP Server について
概要はまだありません
KubeSphere MCP Server の設定
KubeSphere MCP Server のツール
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。
概要
What is KubeSphere MCP Server?
The KubeSphere MCP Server is a Model Context Protocol (MCP) server that integrates with KubeSphere APIs, enabling AI agents to retrieve resources from KubeSphere. It provides four tool modules: Workspace Management, Cluster Management, User and Roles, and Extensions Center.
How to use KubeSphere MCP Server?
You need a KubeSphere cluster with an access address, username, and password. First generate a KSConfig file (YAML format, similar to kubeconfig) containing cluster connection details. Then obtain the ks-mcp-server binary by building from source (go build -o ks-mcp-server cmd/main.go) or downloading from GitHub releases. Finally, configure the MCP server in your AI agent (e.g., Claude Desktop or Cursor) using the stdio transport, specifying the --ksconfig path and optionally --ks-apiserver for HTTP access.
Key features of KubeSphere MCP Server
- Integrates KubeSphere APIs via the Model Context Protocol.
- Provides four dedicated tool modules for resource management.
- Uses a KSConfig file similar to kubeconfig for authentication.
- Supports both HTTPS and HTTP connections (HTTPS required by default).
- Allows optional base64-encoded CA certificates for HTTPS.
- Available as a standalone Go binary or prebuilt release artifact.
Use cases of KubeSphere MCP Server
- Query workspace resources and configurations from an AI assistant.
- Manage clusters and their metadata within a KubeSphere environment.
- Retrieve user and role information for access control auditing.
- Explore and interact with the KubeSphere Extensions Center.
よくある質問
How do I create the KSConfig file?
The KSConfig is a YAML file with `apiVersion`, `clusters`, `contexts`, `current-context`, `kind`, `preferences`, and `users` fields. The default context name is `kubesphere` (can be overridden with `KUBESPHERE_CONTEXT` environment variable). You must provide the server address (HTTPS) and user credentials; the CA certificate field is optional.
Can I use HTTP instead of HTTPS?
Yes. In the KSConfig, set an arbitrary HTTPS address, then pass the actual HTTP address via the `--ks-apiserver` argument when running the server (e.g., `--ks-apiserver http://172.10.0.1:30880`).
How do I obtain the ks-mcp-server binary?
Either build it with `go build -o ks-mcp-server cmd/main.go` or download a precompiled release from the GitHub releases page, then place it in your `$PATH`.
How do I configure KubeSphere MCP Server in an AI agent?
Add an entry to your agent’s MCP configuration (e.g., Claude Desktop’s `claude_desktop_config.json`) with `command: "ks-mcp-server"` and `args` including `stdio`, `--ksconfig <absolute path>`, and optionally `--ks-apiserver <address>`. The agent will then communicate via stdio.
「その他」の他のコンテンツ
MaxKB
1Panel-dev🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
22.0K
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
15.9K
LoadOptimizer
LoadOptimizer plans truck, container and pallet loads with a real optimization engine, straight from your AI assistant. Describe the order in plain language, for example "plan 36 Euro pallets on a standard 13.6 m trailer
DeepMark
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.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
23.6K
コメント