{
  "markdown": "<p align=\"center\">\n  <a href=\"https://www.managelm.com\">\n    <img src=\"https://www.managelm.com/assets/ManageLM.png\" alt=\"ManageLM\" height=\"50\">\n  </a>\n</p>\n\n<h3 align=\"center\">Claude Code Extension</h3>\n\n<p align=\"center\">\n  Manage Linux &amp; Windows servers directly from Claude using natural language.\n</p>\n\n<p align=\"center\">\n  <a href=\"LICENSE\"><img src=\"https://img.shields.io/badge/license-Apache--2.0-blue\" alt=\"License\"></a>\n  <a href=\"https://www.managelm.com\"><img src=\"https://img.shields.io/badge/website-managelm.com-cyan\" alt=\"Website\"></a>\n  <a href=\"https://www.managelm.com/plugins/claude.html\"><img src=\"https://img.shields.io/badge/docs-full%20documentation-green\" alt=\"Docs\"></a>\n  <a href=\"https://github.com/managelm/claude-extension/releases\"><img src=\"https://img.shields.io/github/v/release/managelm/claude-extension\" alt=\"Release\"></a>\n</p>\n\n<p align=\"center\">\n  <img src=\"assets/screenshot.png\" alt=\"Claude managing a Linux server — creating users, managing SSH keys\" width=\"600\">\n</p>\n\n---\n\nAsk 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.\n\n## Features\n\n- **Natural language** — describe tasks in plain English; Claude picks the right skill and parameters\n- **31 built-in skills** — packages, services, firewall, web servers, databases, Docker, certificates, VPN, Kubernetes, and more\n- **Multi-server targeting** — run on a single server, a group, or broadcast to all agents\n- **File transfers** — upload and download files (text and binary) between local and remote\n- **Security audits** — run audits, search findings across your fleet, remediate issues\n- **Task history & revert** — review what changed, inspect diffs, revert any task\n- **Cross-infrastructure search** — find agents by health/OS, search inventory, security findings, SSH keys, sudo rules\n- **Zero inbound ports** — agents connect outbound only; no SSH, no open ports on your servers\n\n## Quick Start\n\n### 1. Install\n\n```bash\nclaude mcp add managelm --transport url https://app.managelm.com/mcp\n```\n\nOr add manually to `~/.claude/settings.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"managelm\": {\n      \"type\": \"url\",\n      \"url\": \"https://app.managelm.com/mcp\"\n    }\n  }\n}\n```\n\n### 2. Authenticate\n\nManageLM 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](https://app.managelm.com/register) (free for up to 10 agents).\n\n### 3. Use it\n\n```\n> Check disk usage on web-prod-01\n\n> Install nginx on all servers in the staging group\n\n> Upload my local config.yml to /etc/myapp/config.yml on db-primary\n\n> Run a security audit on all production servers\n\n> Which servers have CPU usage above 80%?\n\n> Create a user deploy with my SSH key on web-prod-01\n```\n\n## Architecture\n\n```\nClaude ── MCP ──> ManageLM Portal ── WebSocket ──> Agent on Server\n                  (cloud control      (outbound       (local LLM,\n                   plane)              only)            skill exec)\n```\n\nEvery task dispatched to an agent is cryptographically signed (Ed25519). Agents use a local LLM — your data never leaves your infrastructure.\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| `base` | Read-only utilities — files, system info, monitoring, diagnostics |\n| `system` | OS config, performance tuning, hostname, timezone, kernel |\n| `packages` | Install, remove, update across apt/dnf/yum/pacman/zypper/apk |\n| `services` | Systemd units, cron jobs, logs, process control |\n| `users` | Accounts, groups, SSH keys, sudo, password policies |\n| `network` | Interfaces, routes, DNS, ports, connectivity |\n| `security` | Audits, fail2ban, SSH hardening, SELinux/AppArmor, SSL/TLS |\n| `files` | Read, write, upload, download files (text and binary) |\n| `firewall` | iptables, nftables, firewalld, ufw |\n| `docker` | Containers, images, compose, volumes, networks |\n| `nginx` | Server blocks, reverse proxy, SSL, load balancing |\n| `apache` | Virtual hosts, modules, SSL, configuration |\n| `mysql` | Databases, users, queries, backups, replication |\n| `postgresql` | Databases, roles, queries, backups, extensions |\n| `kubernetes` | Pods, deployments, services, logs, kubectl |\n| ...and more | Backup, certificates, git, DNS, VPN, LLM server, etc. |\n\n## Discovery & Management Tools\n\n| Tool | Description |\n|------|-------------|\n| `search_agents` | List all servers (status, OS, health, groups) or filter by CPU/memory/disk, OS, status, group |\n| `get_agent_info` | Detailed info for a single server |\n| `search_inventory` | Search packages, services, containers across fleet |\n| `search_security` | Search security findings across fleet |\n| `run_security_audit` | Trigger a security audit on one or more servers |\n| `run_inventory_scan` | Trigger an inventory scan |\n| `get_task_status` | Check status of running/completed tasks |\n| `get_task_changes` | View file diffs from a task |\n| `revert_task` | Undo file changes from a previous task |\n| `send_email` | Send yourself a report or summary |\n\n## Portal\n\n<p align=\"center\">\n  <img src=\"assets/portal.png\" alt=\"ManageLM Portal — server management, health monitoring, command history\" width=\"700\">\n</p>\n\n## Self-Hosted\n\nReplace `app.managelm.com` with your own portal URL in the MCP configuration. See the [self-hosted guide](https://www.managelm.com/doc/) for Docker deployment.\n\n## Requirements\n\n- **Claude Code v1.0.33+** or Claude Desktop with MCP support\n- **ManageLM account** — [sign up free](https://app.managelm.com/register) (up to 10 agents)\n- **ManageLM Agent** — installed on each server you want to manage\n\n## Other Integrations\n\nManageLM works with your favorite tools:\n\n- [VS Code Extension](https://github.com/managelm/vscode-extension) — `@managelm` in Copilot Chat\n- [ChatGPT Plugin](https://github.com/managelm/openai-gpt) — manage servers from ChatGPT\n- [n8n Plugin](https://github.com/managelm/n8n-plugin) — infrastructure automation workflows\n- [Slack Plugin](https://github.com/managelm/slack-plugin) — notifications and commands in Slack\n- [OpenClaw Plugin](https://github.com/managelm/openclaw-plugin) — OpenClaw integration\n\n## Links\n\n- [Website](https://www.managelm.com)\n- [Full Documentation](https://www.managelm.com/plugins/claude.html)\n- [Portal](https://app.managelm.com)\n\n## License\n\n[Apache 2.0](LICENSE)\n",
  "bytes": 6653,
  "sha": "6b4fdbfe48d95838f7e0f313fdc7eb19c091621f97c9ee918e89019d6b3b6b55",
  "repo_slug": "managelm/claude-extension",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_managelm_claude_extension_managelm_dfc8cd10/readme"
}