managelm

Claude Code Extension

Manage Linux & Windows servers directly from Claude using natural language.

---

Ask Claude to check system status, manage packages, configure services, transfer files, run security audits, and more — across one server or an entire fleet. The extension connects Claude to your infrastructure through MCP (Model Context Protocol), a secure cloud portal, and lightweight agents running on your servers.

Features

• Natural language — describe tasks in plain English; Claude picks the right skill and parameters
• 31 built-in skills — packages, services, firewall, web servers, databases, Docker, certificates, VPN, Kubernetes, and more
• Multi-server targeting — run on a single server, a group, or broadcast to all agents
• File transfers — upload and download files (text and binary) between local and remote
• Security audits — run audits, search findings across your fleet, remediate issues
• Task history & revert — review what changed, inspect diffs, revert any task
• Cross-infrastructure search — find agents by health/OS, search inventory, security findings, SSH keys, sudo rules
• Zero inbound ports — agents connect outbound only; no SSH, no open ports on your servers

Quick Start

1. Install

claude mcp add managelm --transport url https://app.managelm.com/mcp

Or add manually to ~/.claude/settings.json:

{
  "mcpServers": {
    "managelm": {
      "type": "url",
      "url": "https://app.managelm.com/mcp"
    }
  }
}

2. Authenticate

ManageLM uses OAuth 2.0 with Dynamic Client Registration (RFC 7591). On first connection, Claude self-registers as an OAuth client and opens your browser to authorize access — no client ID or secret to copy. All you need is a ManageLM account (free for up to 10 agents).

3. Use it

> Check disk usage on web-prod-01

> Install nginx on all servers in the staging group

> Upload my local config.yml to /etc/myapp/config.yml on db-primary

> Run a security audit on all production servers

> Which servers have CPU usage above 80%?

> Create a user deploy with my SSH key on web-prod-01

Architecture

Claude ── MCP ──> ManageLM Portal ── WebSocket ──> Agent on Server
                  (cloud control      (outbound       (local LLM,
                   plane)              only)            skill exec)

Every task dispatched to an agent is cryptographically signed (Ed25519). Agents use a local LLM — your data never leaves your infrastructure.

Available Skills

Skill	Description
base	Read-only utilities — files, system info, monitoring, diagnostics
system	OS config, performance tuning, hostname, timezone, kernel
packages	Install, remove, update across apt/dnf/yum/pacman/zypper/apk
services	Systemd units, cron jobs, logs, process control
users	Accounts, groups, SSH keys, sudo, password policies
network	Interfaces, routes, DNS, ports, connectivity
security	Audits, fail2ban, SSH hardening, SELinux/AppArmor, SSL/TLS
files	Read, write, upload, download files (text and binary)
firewall	iptables, nftables, firewalld, ufw
docker	Containers, images, compose, volumes, networks
nginx	Server blocks, reverse proxy, SSL, load balancing
apache	Virtual hosts, modules, SSL, configuration
mysql	Databases, users, queries, backups, replication
postgresql	Databases, roles, queries, backups, extensions
kubernetes	Pods, deployments, services, logs, kubectl
...and more	Backup, certificates, git, DNS, VPN, LLM server, etc.

Discovery & Management Tools