troubleshoot-mcp-server
The MCP Server for Kubernetes Support Bundles is designed for AI-driven analysis and troubleshooting of Kubernetes clusters. It enables comprehensive interaction with support bundles, focusing on features like bundle management and secure command execution. This server is particularly notable for its containerization capabilities.
MCP Server for Kubernetes Support Bundles
A Model Context Protocol (MCP) server allowing AI models to interact with Kubernetes support bundles. Key features include bundle management, command execution, file exploration, secure authentication, and container support. The server facilitates analysis and troubleshooting of Kubernetes clusters by AI models. For quick start, users can utilize Podman or manually install using Python. Comprehensive documentation and guides are available for installation, configuration, and development. The project structure includes directories for documentation, examples, scripts, source code, and tests.
Features
- Bundle Management: Initialize and manage Kubernetes support bundles
- Command Execution: Run kubectl commands against bundle's API
- File Explorer: Navigate and search files
- Secure Authentication: Token-based access
- Container Support: Deploy as a containerized app
Requirements
- Python 3.13
kubectltoolsbctltool- Authentication token (
SBCTL_TOKENorREPLICATEDenvironment variable)
Development
- Clone the repository and set up the environment
- Code style is managed by Black and Ruff
- Comprehensive testing support with pytest
- Contributions are encouraged