MCP Cluster Api

@linode

代码仓库

基本信息

分类

开发工具

传输方式

stdio

作者

linode

提交者

Tarun Chinmai Sekar

关于 MCP Cluster Api

暂无概览

#capi#mcp #kubernetes#cluster-management

MCP Cluster Api 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "capi-mcp": {
      "command": "/absolute/path/to/capi-mcp/bin/capi-mcp",
      "env": {
        "KUBECONFIG": "/absolute/path/to/your/kubeconfig.yaml"
      }
    }
  }
}

MCP Cluster Api 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Mcp Cluster Api?

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.

How to use Mcp Cluster Api?

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.

Key features of Mcp Cluster Api

List all CAPI clusters in your environment
Get detailed cluster information and kubeconfigs
Check upgrade eligibility for target Kubernetes versions
List and inspect machines across clusters
Perform control plane rollout (write operation, requires RBAC permissions)
Debugging prompts for cluster and machine issues

Use cases of Mcp Cluster Api

Querying the status of CAPI-managed clusters from AI assistants
Generating kubeconfigs for accessing workload clusters
Checking safe upgrade paths before version changes
Debugging cluster or machine issues with step-by-step guidance
Triggering control plane rolling updates in natural language

常见问题

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.

How do I install and build the server?

Clone the repository and run `make build` to compile the binary.

How do I use it with Claude Desktop?

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.

What tools does the server provide?

Tools include `list_clusters`, `get_cluster`, `get_cluster_kubeconfig`, `check_upgrade

开发工具分类下的更多 MCP 服务器

Hermoso

Hermoso is an AI marketing agent and AI ad generator you run from your AI agent: a remote MCP server that researches the ads already winning in your market, makes image and video ads and organic posts in your brand, publ

Just Domain.

Just.

Just Domain is the domain registrar for businesses built with AI. An AI assistant checks availability and both prices, first year and renewal, and hands back a checkout link for justdomain.ai. Read only by design: no pur

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

LocalCan

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.

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up