Kube Core MCP
MCP del núcleo de Kube
Un servicio de procesamiento de comandos de Kubernetes que convierte solicitudes de lenguaje natural en comandos kubectl válidos.
Características
Conversión de lenguaje natural a comandos de kubectl
Validación de comandos y comprobaciones de seguridad
Compatibilidad con operaciones comunes de kubectl
Integración de AWS Bedrock para el procesamiento de LLM
Related MCP server: MCP Remote Server for Kubernetes
Prerrequisitos
Python 3.8+
Credenciales de AWS configuradas
kubectl instalado y configurado
Node.js y npm (para frontend)
Configuración
Clonar el repositorio:
git clone <repository-url>
cd kube-core-mcpCrear y activar un entorno virtual:
python3 -m venv venv
source venv/bin/activate # On Windows: .\venv\Scripts\activateInstalar dependencias:
pip install -r requirements.txtConfigurar las credenciales de AWS:
export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_REGION=your_regionInicie el servidor FastAPI:
python src/server.pyDocumentación de la API
Chequeo de salud
curl http://localhost:3000/healthServicios
curl http://localhost:3000/api/servicesComandos de lenguaje natural
curl -X POST http://localhost:3000/api/nl \
-H "Content-Type: application/json" \
-d '{"message": "show me the pods in default namespace"}'Comandos directos
curl -X POST http://localhost:3000/api/command \
-H "Content-Type: application/json" \
-d '{"command": "kubectl get pods -n default"}'Seguridad
El servicio funciona en dos modos de seguridad:
ESTRICTO (predeterminado):
Solo permite patrones de comando predefinidos
Valida todos los comandos contra patrones permitidos
Previene operaciones peligrosas
PERMISIVO:
Permite patrones de comando más flexibles
Aún mantiene controles de seguridad básicos.
Útil para desarrollo y pruebas.
Desarrollo
Ejecución de pruebas
pytest tests/Estilo de código
black src/ tests/
flake8 src/ tests/Contribuyendo
Bifurcar el repositorio
Crear una rama de características
Realiza tus cambios
Ejecutar pruebas
Enviar una solicitud de extracción
Licencia
[Agregar información de licencia]
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseBqualityDmaintenanceA server that enables LLMs to manage Kubernetes clusters through natural language commands, wrapping kubectl operations to provide a simplified interface for common Kubernetes tasks.2510
- AlicenseNot gradedqualityDmaintenanceProvides Kubernetes cluster management capabilities through natural language via MCP protocol over HTTP/SSE. Supports Pod, Service, Deployment operations, log retrieval, and resource management with JWT authentication and RBAC permissions.1MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants to interact with Kubernetes clusters by translating natural language into kubectl and Helm operations. It allows users to query, manage, and diagnose Kubernetes resources and cluster states through a seamless integration.20Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables secure Kubernetes operations with configurable security modes, supporting core Kubernetes resources, Istio service mesh, and Helm chart management through natural language.1
Related MCP Connectors
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
GibsonAI MCP server: manage your databases with natural language
Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Jess321995/kube-core-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server