Kubernetes MCP
The Kubernetes MCP Server is a tool that provides secure read-only access to Kubernetes resources for debugging and inspecting the cluster status. It supports multi-cluster switching, CRD resources, and intelligent resource discovery, emphasizing security and high performance.
rating : 2.5 points
downloads : 5.9K
What is the Kubernetes MCP Server?
The Kubernetes MCP Server is a Model Context Protocol (MCP) service that provides secure, read-only access to Kubernetes cluster resources. This tool can be used for debugging, monitoring, and inspecting Kubernetes resources without affecting the normal operation of the cluster.How to use the Kubernetes MCP Server?
Through simple command-line installation or building, you can quickly start the MCP Server and use various functions to query and analyze resources in the Kubernetes cluster. It supports multi-cluster switching, custom configuration, and rich resource discovery capabilities.Use Cases
The Kubernetes MCP Server is particularly suitable for developers, operations engineers, and system administrators to perform secure resource inspection and debugging in the production environment. It can be used to monitor the cluster status, troubleshoot problems, and understand the resource distribution.Main Features
Read-only Secure Access
Ensure that you can only view Kubernetes resources and cannot perform any modification or deletion operations to protect the cluster security.
CRD Support
Supports all Custom Resource Definitions (CRDs) and can seamlessly access custom resources.
Multi-cluster Support
Easily switch between multiple Kubernetes clusters and manage resources in different environments.
Intelligent Resource Discovery
Search for resources related to specific projects through substrings of the API group name, such as FluxCD, ArgoCD, etc.
High-performance Query
Efficiently execute resource queries, supporting filtering, pagination, and complex filtering conditions.
Comprehensive Toolset
Provides a variety of tools, including listing resources, describing resources, getting Pod logs, listing events, and listing contexts.
Advantages
Provides secure read-only access to prevent accidental changes to cluster resources.
Supports all Kubernetes resource types and CRDs for comprehensive monitoring.
Highly efficient performance, supporting complex queries and large-scale data processing.
Easy to use, just start with simple commands.
Supports multi-cluster operations for convenient cross-environment resource management.
Limitations
Does not support creating, updating, or deleting resources, only viewing.
Requires certain Kubernetes knowledge to use effectively.
May require more advanced configuration for very complex queries.
How to Use
Install the MCP Server
Install the MCP Server via Go or build it from the source code. Make sure your system has Go 1.24 or higher installed.
Configure Kubeconfig
Ensure that your kubeconfig file is correctly set so that the MCP Server can access the Kubernetes cluster.
Start the MCP Server
Run the MCP Server and connect using the default kubeconfig file.
Use the Tools
Use the provided tools, such as list_resources, describe_resource, get_pod_logs, etc., to query and analyze Kubernetes resources.
Usage Examples
View Pods in a Specific Namespace
Use the MCP Server to list all Pods in the default namespace to monitor the application status.
Get Logs of a Specific Pod
Get the logs of the Pod named nginx-pod to diagnose application problems.
Find FluxCD Resources
Use the groupFilter parameter to find all FluxCD-related resources, such as HelmReleases and Kustomizations.
Frequently Asked Questions
Is the MCP Server secure?
How to select different Kubernetes contexts?
What resource types does the MCP Server support?
What is the performance of the MCP Server?
Related Resources
GitHub Repository
Source code and documentation for the Kubernetes MCP Server.
Kubernetes Official Documentation
Official documentation for Kubernetes to help you gain in-depth understanding of Kubernetes concepts and operations.
MCP Protocol Specification
Official specification and description of the Model Context Protocol (MCP).

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
16.6K
4.3 points

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
14.8K
4.5 points

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
24.6K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
44.0K
4.3 points

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#
19.2K
5 points

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
44.5K
4.5 points

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
14.8K
4.5 points

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
30.3K
4.8 points
