k8s-mcp-server and mcp-for-argocd
These tools are complements that work together—k8s-mcp-server provides general Kubernetes command execution for AI assistants, while mcp-for-argocd specializes in integrating with Argo CD's declarative GitOps workflow, allowing an AI assistant to both execute raw kubectl commands and manage Argo CD deployments through a unified MCP interface.
About k8s-mcp-server
alexei-led/k8s-mcp-server
K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI systems to assist with cluster management, troubleshooting, and deployments
# Technical Summary Implements MCP via stdio, HTTP streamable, and SSE transports—with stdio as the Claude Desktop default—enabling bidirectional command execution without polling. Runs as a non-root containerized process with command validation and Unix tool piping (`jq`, `grep`, `sed`) for output processing, plus native cloud provider authentication for AWS EKS, GKE, and Azure AKS. Integrates directly into Claude Desktop through simple JSON configuration, allowing natural-language Kubernetes operations without leaving the interface.
About mcp-for-argocd
argoproj-labs/mcp-for-argocd
An implementation of Model Context Protocol (MCP) server for Argo CD.
Exposes 15+ Argo CD management tools covering cluster operations, application lifecycle (create/update/sync/delete), and resource inspection including workload logs and event tracking. Uses stdio and HTTP stream transports with environment-based authentication, supporting direct integration into VS Code, Claude Desktop, and Cursor with optional read-only mode for restricted access.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work