Best MCP servers for DevOps automation
DevOps automation is about giving an agent the keys to the infrastructure: provisioning resources, inspecting deployments, restarting a stuck service, rolling out a container, without a human translating intent into a dozen CLI invocations. An agent wired into your cloud and orchestration layer can answer operational questions and take action in one motion, but the right server depends on where your workloads run, a hyperscaler, a container orchestrator, or the local container runtime under your build. The recurring need is the same: let the agent query and operate real infrastructure safely. The servers below cover the common shapes, each a real MCP server with a verified, current install config.
AWS (AWS Labs)
AWS Labs
Run any AWS CLI command from an agent, with validation, read-only mode, and command suggestions.
The AWS server gives an agent broad reach across AWS services, inspecting resources, querying configuration, and operating infrastructure, the default when your stack lives on Amazon's cloud.
Google Cloud Run
Google Cloud
Google Cloud's official Cloud Run MCP server: deploy local code or file contents to Cloud Run, list and inspect services, and read service logs from your agent.
The Google Cloud server lets an agent query and manage GCP resources, the natural fit for teams whose compute, storage, and networking run on Google Cloud.
Kubernetes
containers (Red Hat)
Native Kubernetes and OpenShift MCP server: list, inspect, and manage cluster resources, pods, and Helm releases directly through the Kubernetes API.
The Kubernetes server lets an agent inspect pods, deployments, and logs and apply changes to a cluster, essential for diagnosing and operating containerized workloads.
Docker
Docker
Docker's official MCP Gateway: run, secure, and aggregate containerized MCP servers behind one endpoint, with on-demand discovery from the Docker MCP Catalog.
The Docker server lets an agent list, build, run, and inspect containers and images on the local runtime, ideal for managing the container layer during builds and local environments.