AI Hosting
Deploy Claude Code, Codex, OpenClaw, Hermes, Paperclip, Odysseus or n8n onto a server you own. Then run that server by telling your agent what you want.
Free plan: 1 server, 10 sites, and MCP, Agent Skills and the Public API included. No card.
Anything that speaks Streamable HTTP MCP connects too.
One account, two directions
Agents you already use reach in and operate your infrastructure. Agents you deploy live inside it. Same account, same panel, same bill.
Agentic setup
Do it yourself in a minute, or hand the whole thing to the agent you already use.
claude mcp add xcloud --transport http https://app.xcloud.host/mcpCreate free accountPaste one line into Claude Code, Codex or Cursor. It reads our setup file, connects the MCP server and installs the skills, and stops only for the two steps a human has to do: the browser sign-in and a restart.
Set up xCloud by following https://xcloud.host/agent-setup/prompt.md
Three doors, same account
All three are free with every xCloud account and reach the same operations. They differ in what you set up, and in what holds the credentials.
# Claude Codeclaude mcp add xcloud --transport http https://app.xcloud.host/mcp
# Codexcodex mcp add xcloud --url https://app.xcloud.host/mcp
# Anything that takes an mcpServers block{ "mcpServers": { "xcloud": { "url": "https://app.xcloud.host/mcp" } } }
# Stdio-only clientsnpx mcp-remote https://app.xcloud.host/mcp
OAuth fires the first time your agent reaches for an xCloud tool, so no token sits in a config file. Headless and CI use a token scoped to mcp:invoke.
claude plugin marketplace add xCloudDev/xcloud-agent-skillsclaude plugin install xcloud@xcloud-agent-skills# then /reload-plugins to activate
xcloud:deploy | Git, Docker and one-click deploys, staging, new WordPress sites |
|---|---|
xcloud:troubleshoot | Why a site errors: status, events, logs, services |
xcloud:performance | Why a site is slow: cache layers, PageSpeed, PHP |
xcloud:servers | PHP, services, cron, firewall, fail2ban, reboots |
xcloud:sites | Backups, domains, cache, SSH, git settings, staging |
xcloud:wordpress | Plugins, themes, updates, magic login, vulnerabilities |
xcloud:ssl | Certificates: view, install, renew, delete |
xcloud:billing | Plan, invoices, subscriptions, add-ons |
xcloud:account | Teams, alerts, API tokens, integrations, blueprints |
# no auth on /healthcurl -s https://app.xcloud.host/api/v1/health{"status":"ok","version":"v1"}
Full Accessread:serverswrite:serversread:siteswrite:sitesread:billingread:addonswrite:addonsmcp:invokeWrite operations are asynchronous: they return a task you poll, not a finished resource. Build in polling and a timeout.
Your agent can only do what the token you gave it allows. Risky changes ask first, backups run before anything is touched, and the skills wait for the job to finish instead of assuming it did.
Free
MCP, Agent Skills and the Public API, on every account
Sign in with OAuth in the browser. Access is scoped to your team and you can revoke it from the dashboard at any time.
Give each token only what its job needs: read:servers, write:sites, read:billing, mcp:invoke and more.
The skills back up before a bigger change and wait for the job to finish, then point you to the one-click restore.
In practice
No endpoints, no resource IDs, no menu to find. Your agent maps the sentence to the right operation, runs the steps in order, and waits for each one to finish.
xcloud:wordpressxcloud:serversxcloud:sslxcloud:serversxcloud:sitesxcloud:sitesGet going
An agent from the list below, or your own stack from Git or a Docker Compose file.
One MCP URL works for every client: Claude Code, Cursor, Codex, Windsurf and the rest.
"Build me a site." "Why is this slow?" "Back it up." Your agent picks the right skill and does the work.
The agents
Everything you can deploy, sorted by the job rather than the brand. Each links to its own setup steps and pricing.
| I want… | Deploy | How you reach it | From |
|---|---|---|---|
| a coding agent that keeps working after I close the laptop | Claude Code | Terminal, Claude web and mobile apps | $5.00/mo |
| to put the app Codex built on a real domain | Codex | Your own domain, redeployed on git push | $5.00/mo |
| an open-source coding agent I can extend with plugins | DeepSeek Harness | A managed Cloud VPS, your choice of models and tools | $9.99 first month, then $19.99/mo |
| an assistant I can text like a person | OpenClaw | Telegram, set up for you | $9.99 first month, then $19.99/mo |
| an agent that remembers everything between conversations | Hermes | Telegram, plus your tools, files and APIs | $9.99 first month, then $19.99/mo |
| a workforce of agents with roles and budgets | Paperclip | Its own dashboard | $9.99 first month, then $19.99/mo |
| a private AI workspace: chat, memory, research, documents | Odysseus | A private web workspace from a Docker Compose file, your own LLM keys | $5.00/mo |
| to automate the plumbing between all of the above | n8n | 500+ integrations, webhooks, AI nodes. Needs 4 GB RAM | $24.00/mo |
| to run something that is not on this list | Your own stack | Deploy from Git, or a Docker Compose file | $3.00/server/mo |
Included
Fast hardware, a hardened network and monitoring come with every server, with nothing extra to configure.
Hardware
Security
AI Bot Blocker is configurable, so you choose whether crawlers like GPTBot can read your sites.
Recovery
On standard managed servers. AI-agent plans do not include backups.
Visibility
100,000+ websites
“…I reluctantly switched from RunCloud after my Server specialist showed me a lifetime deal…I took it. And have been super happy with all that you offer. With over 160 websites now, I have my AI (Clawbot) scanning and reviewing my servers daily.”
Founder, Designs By Dave O.
Shipped
Dated straight from the changelog.
Agents find the right operation, validate inputs before running, and recover failed deployments. Plus multi-team API access.
Read the releaseAn open-source, plugin-based AI coding agent on fully managed infrastructure.
Read the releaseIncluding Penpot, SearXNG, ClickHouse, Discourse, Keycloak and Gitea.
Read the releaseManage servers and sites in plain language; the skills make the Public API calls for you.
Read the releaseFAQ
What is free, which door to use, what an agent server can and cannot do, and why the prices differ.
The control plane is free. MCP, the AI Agent Skills and the Public API are included with every xCloud account, including the free plan, so there is no add-on and nothing to upgrade. You pay only when you run something: a server. Your AI assistant's own model usage is billed by its provider, not by us.
MCP first. It is one endpoint, it works with every MCP-compatible client, and OAuth means there is no token to paste. The Skills add ready-made workflows on top: the plugin installs into Claude Code, and the same nine skills ship as a portable Agent Plugins package for ChatGPT and Codex, Cursor, GitHub Copilot, Kiro and VS Code. Install both if your agent is on that list.
Read the MCP docsBecause they are different products. Claude Code, Codex and Odysseus run on a standard managed server, from $5.00/mo; n8n needs 4 GB of RAM, so it starts on the $24.00/mo plan. OpenClaw, Hermes, Paperclip and DeepSeek Harness run on a Cloud VPS sized for an always-on agent: $9.99 for the first month, then $19.99/mo.
Compare every planBoth. Connect Anthropic, OpenAI, OpenRouter, Moonshot AI (Kimi) or Gemini today, with Grok, xAI and Mistral coming. And you can run any of this on an xCloud Managed Server or on your own machine at DigitalOcean, Vultr, Linode, AWS or another provider.
No. You bring your own key from Anthropic, OpenAI, OpenRouter, Moonshot AI (Kimi) or Gemini, and model usage is billed by that provider.
No. Each AI-agent server runs one agent. For websites, Docker apps or one-click apps, use a standard managed server.
Telegram is set up for you. WhatsApp is not bundled as a native channel.
OpenClaw hostingIn the dashboard under Settings → Developers → MCP. The endpoint is https://app.xcloud.host/mcp for every client.
Yes. Ask it to follow https://xcloud.host/agent-setup/prompt.md. It connects the MCP server and installs the skills itself, and stops only for the browser sign-in and a restart.
It acts only with the permissions on the token you issued, and access is scoped to your team. Destructive tools ask for confirmation before they run, the skills take a backup before a bigger change, and you can revoke access from the dashboard at any time.
For agents
Point an AI agent at these instead of scraping the page. They are the canonical source.
The free plan gets you a server, ten sites and the whole control plane (MCP, Agent Skills and the Public API), with no card.
