Task-based pick
DevOps
Tools for infrastructure: access to Kubernetes and Docker, server and CI management through an agent. For devops engineers ready to give an agent hands in production. Every entry has an install command and a risk level, usually high, stating exactly what the tool changes in the system.
12 tools
Tools in this pick
MCP server for Kubernetes: the agent reads cluster state, diagnoses pod failures and runs operations through kubectl
Kubernetes MCP
MCP Server Kubernetes
MCP server for managing a Kubernetes cluster through kubectl and Helm, with a non-destructive mode
A Go MCP server for Kubernetes and OpenShift: resources, pods, logs, Helm and Tekton straight through the cluster API
MCP server for managing Docker in natural language: containers, images, networks and volumes, including remote hosts over SSH
The docker mcp CLI plugin and gateway: MCP servers from Docker's catalog in isolated containers behind one connection point
A self-hosted gateway that merges several MCP servers into one endpoint with auth and tool selection
An AI assistant for Kubernetes that turns plain-language requests into kubectl operations and doubles as an MCP server
A Go MCP server for Kubernetes: read any cluster resource and pod logs, with apply and exec in write mode
AWS's official MCP server suite: docs, IaC, containers, serverless, databases, cost and monitoring
Jira, Confluence, Bitbucket and Jenkins MCP
Sberworks MCP
A local stdio MCP server for self-hosted Jira, Confluence, Bitbucket Server and Jenkins, with mTLS support and write tools disabled by default
An MCP server and skills on top of Kubernetes network observability: an agent investigates incidents and queries cluster traffic through an eBPF-built index
An open-source Kubernetes UI with a built-in MCP server: the agent inspects the cluster, diagnoses breakages and operates it with RBAC in mind
FAQ
Is it safe in production?
These tools are usually high risk: they change real systems. Start on a test environment and read the limitations section.
Do I need credentials?
Yes, usually a kubeconfig, a token or SSH access. The requirements are listed in each entry.
Collect these tools into a pack and share with one link.