#41 · Primary category: AI DevOps & SRE Tools
kubernetes-mcp-server
Model Context Protocol (MCP) server for Kubernetes and OpenShift
Project last updated:08/28/26
GitHub Stars
2.0K
Forks
427
Contributors
74
License
Apache-2.0
Why we included this project
Kubernetes and OpenShift admins can hand routine cluster work to an LLM through this MCP server, which exposes kubectl-like operations as callable tools. It's written in Go and talks straight to the Kubernetes API, so there's no shell wrapper or extra binaries to maintain, and requests stay fast. Beyond CRUD on any resource, it covers pod logs, exec, resource usage, events, namespaces, and Helm releases, plus Tekton pipeline tasks. It watches kubeconfig changes and can serve multiple clusters from one config, shipping as a single binary for Linux, macOS, and Windows. Anyone already using Claude Desktop, VS Code, or Cursor can connect it and manage clusters conversationally, which is handy for SREs and platform engineers who want an auditable way to let an AI agent touch their infrastructure.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
harness
Harness Open Source is an end-to-end developer platform with Source Control Management, CI/CD Pipelines, Hosted Developer Environments, and Artifact Registries.
nx
The Monorepo Platform that amplifies both developers and AI agents. Nx optimizes your builds, scales your CI, and fixes failed PRs automatically. Ship in half the time.
jenkins
Jenkins automation server
awx
AWX provides a web-based user interface, REST API, and task engine built on top of Ansible. It is one of the upstream projects for Red Hat Ansible Automation Platform.
dagger
Automation engine to build, test and ship any codebase. Runs locally, in CI, or directly in the cloud