Summary

Add support for remote cluster introspection so that OLS users can get cluster specific answers .

----- Prereq from OCP MCP server —

Add support for dynamic Kubernetes cluster targeting through HTTP headers, allowing AI systems to specify cluster endpoints and TLS configuration per-request without requiring pre-configured kubeconfig contexts.

Problem Statement

Currently, the MCP server only supports targeting clusters that are pre-configured in a kubeconfig file via the context parameter. This requires:

1. Pre-configuration: All target clusters must be known and configured ahead of time
2. Static configuration: Cannot dynamically connect to new clusters
3. LLM parameter pollution: Adding dynamic cluster support via tool parameters would require LLMs to understand infrastructure details

For AI systems that need to interact with multiple Kubernetes clusters dynamically (e.g., multi-tenant scenarios, ephemeral clusters, or clusters discovered at runtime), the current approach is limiting.

https://github.com/containers/kubernetes-mcp-server/issues/387