KubeSphere MCP Server

What does “KubeSphere” MCP Server do?

The KubeSphere MCP Server is a Model Context Protocol (MCP) server that provides seamless integration with KubeSphere APIs, enabling AI assistants and LLM-based development tools to access and interact with resources managed by a KubeSphere cluster. By bridging the gap between AI workflows and KubeSphere’s resource management capabilities, this server empowers developers to automate and streamline tasks such as workspace and cluster management, user and role provisioning, and working with extensions. The MCP server offers a suite of tools grouped into four major modules—Workspace Management, Cluster Management, User and Roles, and Extensions Center—enabling AI clients to query, manage, and manipulate KubeSphere resources efficiently to enhance cloud-native development and DevOps workflows.

List of Prompts

No explicit prompt templates are mentioned in the available repository files or documentation.

List of Resources

No explicit MCP resources are detailed in the available repository files or documentation.

List of Tools

• Workspace Management
  Tools for managing workspaces within the KubeSphere environment, such as creating, listing, or deleting workspaces.
• Cluster Management
  Tools that enable management of Kubernetes clusters, including querying cluster status or configurations.
• User and Roles
  Tools to manage user accounts and roles, such as adding users, assigning roles, or retrieving user information.
• Extensions Center
  Tools for interacting with KubeSphere’s Extensions Center, allowing management and integration of additional features or plugins.

Use Cases of this MCP Server

• Workspace Automation
  AI agents can automate the creation, deletion, or modification of workspaces in a KubeSphere cluster, saving developers time on routine setup tasks.
• Cluster Monitoring and Management
  Developers can leverage AI to monitor cluster health, fetch configurations, or trigger cluster-level actions programmatically.
• User and Role Provisioning
  Streamline onboarding and access control by automatically provisioning users and configuring their roles via MCP-driven workflows.
• Extension Management
  Easily manage KubeSphere extensions, enabling dynamic integration of new capabilities into the platform without manual intervention.
• DevOps Workflow Integration
  The MCP server allows AI tools to incorporate KubeSphere resource management into broader DevOps pipelines, enhancing automation and consistency.

How to set it up

Windsurf

No setup instructions for Windsurf are present in the repository.

Claude

1. Ensure you have a KubeSphere cluster and generate a ksconfig file as described in the prerequisites.

2. Download or build the ks-mcp-server binary and place it in your system path.

3. Edit Claude’s MCP configuration file to include the KubeSphere MCP Server:

   {
     "mcpServers": {
       "KubeSphere": {
         "args": [
           "stdio",
           "--ksconfig", "<ksconfig file absolute path>",
           "--ks-apiserver", "<KubeSphere Address>"
         ],
         "command": "ks-mcp-server"
       }
     }
   }
   

4. Replace <ksconfig file absolute path> and <KubeSphere Address> with your actual values.

5. Restart Claude and verify the connection.

Securing API Keys:
Store sensitive credentials, such as cluster usernames and passwords, in environment variables and reference them in your configuration as needed.

Cursor

1. Ensure you have a valid KubeSphere cluster and a ksconfig file.

2. Download or build the ks-mcp-server binary.

3. Edit Cursor’s MCP configuration file as follows:

   {
     "mcpServers": {
       "KubeSphere": {
         "args": [
           "stdio",
           "--ksconfig", "<ksconfig file absolute path>",
           "--ks-apiserver", "<KubeSphere Address>"
         ],
         "command": "ks-mcp-server"
       }
     }
   }
   

4. Fill in the required absolute file paths and addresses.

5. Restart Cursor to apply changes.

Cline

No setup instructions for Cline are present in the repository.

Note on Securing API Keys

Store sensitive information like usernames and passwords in environment variables rather than directly in config files. Example:

{
  "env": {
    "KUBESPHERE_USERNAME": "your-username",
    "KUBESPHERE_PASSWORD": "your-password"
  },
  "inputs": {
    "username": "${KUBESPHERE_USERNAME}",
    "password": "${KUBESPHERE_PASSWORD}"
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "KubeSphere": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “KubeSphere” to your actual MCP server name and replace the URL with your MCP server’s address.

Overview

Our opinion

The KubeSphere MCP Server provides a solid foundation for KubeSphere resource management through AI, with comprehensive instructions for Claude and Cursor. However, documentation on MCP prompt templates, resources, and advanced MCP features (like Roots and Sampling) is lacking. Overall, it is a practical project for basic integration needs, but further documentation would be beneficial.

MCP Score

Rating: 6/10 — Good basic functionality and setup instructions, but limited resource/prompt detail and lack of advanced MCP-specific features documentation.