K

Kubernetes MCP

Kubernetes MCP is a model context protocol server implemented in Go language, specifically designed to interact with Kubernetes clusters. It provides rich Kubernetes resource management functions through the MCP protocol, supports multiple transmission methods, and includes advanced features such as cluster metric monitoring and log analysis.
2.5 points
32

What is the Kubernetes MCP Server?

The Kubernetes MCP Server is a server that implements the Model Context Protocol (MCP) and is specifically designed to interact with Kubernetes clusters. It allows MCP - compatible clients to perform Kubernetes operations through defined tools, such as managing resources, viewing logs, and obtaining cluster information.

How to use the Kubernetes MCP Server?

You can run the server by building the source code or using a Docker image, and then interact with the server through two transmission methods: standard I/O or Server - Sent Events (SSE). The server supports various Kubernetes resource operations and cluster management functions.

Applicable scenarios

Suitable for scenarios that require remote management of Kubernetes clusters, such as automated operations, cluster monitoring, and integration with resource management platforms. It is particularly suitable for environments that require a unified interface to access different Kubernetes clusters.

Main features

MCP protocol implementationFully implements the MCP protocol, supporting both standard I/O and Server - Sent Events transmission methods
Kubernetes cluster interactionInteracts with the Kubernetes cluster using the controller - runtime client, supporting various resource operations
Resource management toolsSupports resource management for multiple Kubernetes API groups, including Core API, Apps, Batch, Networking, etc.
Log analysis functionProvides advanced log analysis functions such as error pattern recognition, time distribution analysis, HTTP status code tracking, and performance metrics
Cluster metrics functionSupports obtaining node, Pod, and cluster resource usage metrics, and identifying applications with the highest resource consumption

Advantages and limitations

Advantages
Supports multiple Kubernetes resource types and operations
Provides a standardized MCP protocol interface for easy integration
Supports two transmission methods to meet different scenario requirements
Rich log analysis and cluster metrics functions
Well - formatted API responses for easy front - end processing
Limitations
The standard I/O transmission method is not fully implemented
Requires a Go 1.24 or higher version environment
Requires permission to access the Kubernetes cluster

How to use

Build or obtain the server
You can obtain the server by building from the source code or using a Docker image
Run the server
Select a suitable transmission method to run the server
Configure cluster access
Ensure that the server can access the Kubernetes cluster, which can be done through kubeconfig or a service account
Connect using a client
Use an MCP - compatible client to connect to the server and start operating the cluster

Usage examples

Get cluster node informationObtain detailed information about all nodes in the Kubernetes cluster through the MCP protocol, including status and resource usage
Deploy a new applicationDeploy a new application in the specified namespace through a YAML manifest file
Troubleshoot Pod issuesObtain the logs and event information of the problematic Pod to help diagnose the problem

Frequently Asked Questions

What is the MCP protocol?
How to configure cluster access permissions?
Which Kubernetes resource types are supported?
How to obtain Pod metric data?

Related resources

GitHub repository
Project source code and latest version
Kubernetes official documentation
Kubernetes official documentation and API reference
MCP protocol specification
Go language implementation library of the MCP protocol
Installation
Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.
Featured MCP Services
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
85
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
140
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
828
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
564
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
282
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
753
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase