Kube Core MCP

A Kubernetes command processing service that converts natural language requests into valid kubectl commands.

Features

• Natural language to kubectl command conversion

• Command validation and security checks

• Support for common kubectl operations

• AWS Bedrock integration for LLM processing

Related MCP server: MCP Remote Server for Kubernetes

Prerequisites

• Python 3.8+

• AWS credentials configured

• kubectl installed and configured

• Node.js and npm (for frontend)

Setup

1. Clone the repository:

git clone <repository-url>
cd kube-core-mcp

2. Create and activate a virtual environment:

python3 -m venv venv
source venv/bin/activate  # On Windows: .\venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Configure AWS credentials:

export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_REGION=your_region

5. Start the FastAPI server:

python src/server.py

API Documentation

Health Check

curl http://localhost:3000/health

Services

curl http://localhost:3000/api/services

Natural Language Commands

curl -X POST http://localhost:3000/api/nl \
  -H "Content-Type: application/json" \
  -d '{"message": "show me the pods in default namespace"}'

Direct Commands

curl -X POST http://localhost:3000/api/command \
  -H "Content-Type: application/json" \
  -d '{"command": "kubectl get pods -n default"}'

Security

The service operates in two security modes:

1. STRICT (default):

   • Only allows predefined command patterns

   • Validates all commands against allowed patterns

   • Prevents dangerous operations

2. PERMISSIVE:

   • Allows more flexible command patterns

   • Still maintains basic security checks

   • Useful for development and testing

Development

Running Tests

pytest tests/

Code Style

black src/ tests/
flake8 src/ tests/

Contributing

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Run tests

5. Submit a pull request

License

[Add License Information]