Servers that give an agent access to something — a filesystem, an API, a database. Every listing here was approved by a person before it appeared, and links out to the source rather than reproducing it. We deliberately don't publish ready-made config blocks: a working one carries arguments and environment variables, and those are somebody's secrets waiting to happen.
90+ production-safe OpenStack tools for AI agents via MCP. Project-scoped & read-only by default. Works with Claude, Open WebUI & any MCP client. FastMCP + Open…
Lightweight self-hosted Docker Compose control plane: Git deployments, HTTPS domains, logs and backups, plus an MCP server so AI agents can deploy with scoped t…
Agentless Windows workflow orchestration. Self-hosted, open source, alternative to System Center Orchestrator with SCOrch workflow import.
Distributed, self-hostable uptime monitoring: 40 check types, multi-region workers, private agents, status pages, incidents and on-call escalation — in a single…
MCP SSH Server: 37 tools for remote SSH management | Claude Code & OpenAI Codex | DevOps automation, backups, database operations, health monitoring
Enfour, Inc. FrontierStack (www.frontierstack.app): Mac and server health, logs, restarts.
A curated, DevOps-focused list of Model Context Protocol (MCP) servers—covering source control, IaC, Kubernetes, CI/CD, cloud, observability, security, and coll…
A modern, container-friendly, optionally-distributed, fault-tolerant, highly available, leader-electing, highly configurable, precompiled, multi-architecture, p…
Detects database migration table locks, terraform cost leaks, and OWASP API flaws.
SDK for creating, managing, and operating Kubernetes clusters and workloads with ease.
Live status-page map for 1,127 SaaS/cloud vendors plus 15,418 historical incidents.
Manage AWS, Hetzner, OVH and SSH servers: status, logs, CloudWatch, IP bans, safe command exec.
Inspect and manage a homelab over MCP - status, Docker, ports, backups - without shell access.
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
Deterministic, offline, read-only ADR decision memory for coding agents. No model or network calls.
Control fleets of remote machines via AI agents: exec, files, git, fleet ops, map/reduce.