What is MCP Server?

MCP (Model Context Protocol) Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. In the context of UBOS Asset Marketplace, it enables AI models to execute Kubernetes commands.

How do I install MCP Kubernetes?

You can install it directly using Go: bash go install github.com/BhagyaAmarasinghe/mcp-kubernetes@latest

How do I start the MCP Kubernetes server?

Run the command mcp-kubernetes. For HTTP transport, use mcp-kubernetes -port 8080.

How can I use MCP Server with Claude Desktop?

Configure Claude Desktop by adding the MCP Kubernetes server to your claude_desktop_config.json:

{ “mcpServers”: { “kubernetes”: { “command”: “mcp-kubernetes” } } }

What commands are available in the MCP Kubernetes server?

The MCP Kubernetes server supports the following MCP requests:

• execute: Executes a kubectl command.
• get-contexts: Retrieves a list of available Kubernetes contexts.
• current-context: Gets the current Kubernetes context.
• set-context: Sets the current Kubernetes context.

What are the security considerations when using MCP Server?

This MCP server executes kubectl commands directly on your machine, so it should only be used in trusted environments. It does not implement authentication or authorization controls by default.

What are the requirements for using MCP Server?

• Go 1.23 or higher
• kubectl installed and in your PATH
• A valid kubeconfig file

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems.

How does MCP Server integrate with the UBOS platform?

The UBOS MCP server allows you to integrate Kubernetes commands into complex workflows involving multiple agents and data sources within the UBOS platform, enabling AI-driven management of your Kubernetes infrastructure.