mcp-kubernetes and ig-mcp-server
About mcp-kubernetes
Azure/mcp-kubernetes
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
Implements a unified `call_kubectl` tool that consolidates operations into a single interface (reducing context overhead compared to legacy multi-tool approaches), while supporting role-based access control through `readonly`, `readwrite`, and `admin` modes that filter operations at registration time. Integrates with kubectl and optional ecosystem tools (Helm, Cilium, Hubble), communicating via stdio transport by default and supporting OpenTelemetry tracing for observability.
About ig-mcp-server
inspektor-gadget/ig-mcp-server
Debug your Container and Kubernetes workloads with an AI interface
Exposes Inspektor Gadget's eBPF-powered kernel observability (DNS traces, TCP connections, syscalls, file activity) as dynamically-registered MCP tools, enabling LLMs to autonomously select relevant gadgets and correlate low-level telemetry across multiple data sources. Supports foreground/background execution modes, read-only production safety, and flexible deployment via stdio, Docker, or Kubernetes HTTP transport. Transforms raw kernel events into structured JSON enriched with Kubernetes metadata (pod, namespace, container), enabling AI-driven root cause analysis grounded in real evidence rather than speculation.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work