mcp-k8s and mcp-kubernetes-server
These are ecosystem siblings, with `feiskyer/mcp-kubernetes-server` potentially being a client or specialized implementation that interacts with the broader Model Control Protocol (MCP) framework, which `silenceper/mcp-k8s` likely represents as a more general server or reference implementation for Kubernetes.
About mcp-k8s
silenceper/mcp-k8s
A Kubernetes MCP (Model Control Protocol) server that enables interaction with Kubernetes clusters through MCP tools.
Implements stdio, SSE, and HTTP transport modes for flexible client integration, with granular permission controls enabling selective enable/disable of read and write operations. Leverages the mcp-go SDK and Kubernetes client-go library to provide CRUD operations on all resource types (including CRDs) and integrated Helm v3 release/repository management. Designed as an intelligent operations assistant for LLM-driven cluster management, supporting natural language problem diagnosis, batch operations, and configuration validation.
About mcp-kubernetes-server
feiskyer/mcp-kubernetes-server
A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning the results in a format the AI tools can understand.
Implements fine-grained access control through optional flags (--disable-kubectl, --disable-helm, --disable-write, --disable-delete) and supports multiple transport protocols (stdio, SSE, streamable-http) for flexible deployment across MCP-compatible clients. Provides both high-level tools (kubectl, helm command execution) and lower-level Kubernetes API wrappers (k8s_get, k8s_describe, k8s_logs, k8s_events) that translate natural language into structured API calls against kubeconfig-authenticated clusters.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work