1,832 servers in Cloud & DevOps
MCP server for NinjaOne RMM — devices, organizations, alerts, and tickets.
Create, test and break real Proxmox VE clusters in QEMU/KVM on the local host.
What changed across metrics, logs and traces, and where it started (Grafana, Victoria, New Relic).
Stdio MCP server for SSH host storage and remote command execution with a connection-pool monitor.
Manage AWS, Hetzner, OVH and SSH servers: status, logs, CloudWatch, IP bans, safe command exec.
SQL-native query and provisioning engine for cloud infrastructure, served over MCP.
Monitor and manage Proxmox VE clusters: VMs, containers, storage and backups. Read-only by default.
Schedule and manage recurring and one-off HTTP jobs on Runhooks from your AI agent.
Deploy and manage apps, databases, volumes and domains on Hostim, an EU cloud hosting platform.
Manage your rented Macs at Halfpenny Mac: list, check online, credentials, restart, update macOS.
MCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
Wait for production to clear each deploy, and read the evidence when a release fails.
Disposable microVM sandboxes for AI agents: run code, read/write files, git, preview URLs.
Deploy and manage SnapDeploy apps from your AI assistant: builds, logs, env vars, add-ons, domains.
Deploy websites, PHP apps and WordPress to kapaweb hosting (DirectAdmin, Plesk preview) from Claude
Live AWS, database & Kafka infrastructure context for AI coding assistants via MCP.
Unofficial MCP server for reading and managing Cloudcraft architecture blueprints
Pre-checks a model change before GPU time or traffic: memory, layout, serving config, pins.
Deploy and run apps from your coding agent. Sign in with one link; no dashboard or Dockerfile.
Self-hostable GPU-aware job broker: submit, route by VRAM, babysit jobs across machines via MCP.
eBPF network observability and safe emergency control for Linux and Kubernetes.
Deploy self-hosted OpenClaw to AWS, GCP, Azure or a local VM — a CLI and an MCP server in one.
The safety gate between AI agents and your servers: typed, policy-checked, audited ops tools.
Set up and run an Epeaky den on a server you already have, over your own SSH.
Ansible checkout truth: module specs, task args, roles, inventory, plays, upgrade impact
Runs non-urgent LLM tasks at the cleanest grid hour before a deadline, via Batch APIs when allowed.
Task-shaped Zabbix access for AI agents: problems, host triage, metrics, maintenance windows.
Dapr state, pub/sub, bindings, secrets, locks, crypto, conversation, actors, invocation as MCP tools
Read-only-by-default MCP server for diagnosing a self-hosted arr stack (Sonarr, Radarr & more).