OpenCode + xCloud
Run Docker apps with OpenCode on xCloud
Running Docker apps with OpenCode means asking the terminal agent that is already open in your repository to scan the Compose file, preview the site on an xCloud Docker server, deploy it after one approval and keep it backed up.
- Skill: xcloud:deploy
- Toolsets: sites, servers
- Free with every xCloud account
YouDeploy this repo to the Frankfurt Docker server. Scan the compose file first.
xcloud_git_compose-scanread-only
AgentTwo services: web publishes 8080, db publishes nothing. Suggested port 8080. Dry run next, on a staging hostname?
YouYes.
xcloud_servers_sites_git_dockerdry run
AgentDry run clean: docker-compose.yml, port 8080, notes-staging.acme.xcloud.site. Create it?
. Keep a human in the loop: xCloud stops and asks before anything that creates, deploys, updates, reboots, deletes or buys.
Setup
How Do You Set Up OpenCode to Run Docker apps on xCloud?
Connect OpenCode once; every job on this account uses the same connection. Then ask in plain words.
Add the xCloud MCP server
Run this from the project that should use xCloud, or add --global to make it available everywhere. OpenCode writes the entry under mcp.servers in its config (OpenCode v2 no longer accepts server names directly under mcp). Remote servers use OAuth by default, so there is nothing else to fill in; the equivalent hand-written entry is shown below.
opencode mcp add xcloud --url https://app.xcloud.host/mcp # the entry it writes to opencode.jsonc { "$schema": "https://opencode.ai/config.json", "mcp": { "servers": { "xcloud": { "type": "remote", "url": "https://app.xcloud.host/mcp" } } } }Sign in with OAuth
This opens your browser on the xCloud approval screen, where you tick the teams and choose Read-only or Full access. Inside OpenCode, /mcps does the same: pick xcloud and sign in. Then opencode mcp list should show xcloud as connected.
opencode mcp auth xcloud opencode mcp listNo browser? Use an API key
For a headless or CI machine, create a token with the mcp:invoke scope plus the read abilities for the areas it will use (read:servers and read:sites, with read:billing and read:addons for billing and add-on tools) and the matching write: abilities if it should change things in Settings, Developers, API Tokens and export it as XCLOUD_TOKEN. Setting oauth to false turns off the automatic sign-in, and the {env:XCLOUD_TOKEN} reference keeps the token out of the file. The entry still lives under mcp.servers.
{ "mcp": { "servers": { "xcloud": { "type": "remote", "url": "https://app.xcloud.host/mcp", "oauth": false, "headers": { "Authorization": "Bearer {env:XCLOUD_TOKEN}" } } } } }Check it worked
Then ask OpenCode for the job itself, for example:
Scan docker-compose.yml in this repo and list the services and published ports xCloud would see.
In practice
How Does Docker apps Work from OpenCode?
OpenCode starts in the directory that holds your Dockerfile or docker-compose.yml, and that is what makes this pairing useful. Before it calls xCloud it can open the Compose file itself and read the services, the ports mappings and the image lines. When the scan then reports the services and the host ports the file publishes, you can compare the two without leaving the terminal. If the file maps 80:80 or publishes nothing at all, OpenCode says so before the dry run. Because it can edit files, it can also propose publishing 127.0.0.1:8080:8080 instead, show you the diff and wait. xCloud runs your Compose file as it is and never rewrites it, so that change has to be committed and pushed before a deploy reads it.
OpenCode prefixes every MCP tool with the server name, so the calls you will see scroll past are xcloud_git_detect, xcloud_git_compose-scan, xcloud_servers_sites_git_docker and later xcloud_sites_docker_backup. The first two are reads and run at once. The Docker create goes out twice: first as a dry run that prints the compose file, the port and any warnings, then again with confirm after you answer yes. OpenCode also decides who may do this. It can switch a server's tools off globally and on for one agent, so you can keep xcloud away from your everyday coding agent and enable it only for an operations agent whose job is this one.
Backups keep the same terse rhythm. Ask for a backup before an upgrade and OpenCode calls the Docker backup tool, which needs no prompt, then reads the backup list until the new row is completed. The app is stopped while the snapshot is captured, so tell it when you are ready. When a deploy fails, it reads the diagnosis, fixes the Dockerfile or Compose file in your working tree and asks before it retries on the same site.
OpenCode specific: Docker tools share OpenCode's context with the other 188 operations. For this job connect https://app.xcloud.host/mcp?toolsets=sites,servers, which covers deploy and backup, so the model is not carrying billing and WordPress tools it will not use. A Docker deploy also needs a Docker server: if OpenCode picks a server with another stack, xCloud answers incompatible_server, and the fix is to name a Docker server, not to retry the same call.
What xCloud does for docker apps
xCloud reads the repository, scans the Compose file for services and ports before anything is created, previews the site with a dry run and deploys it behind its own nginx once you approve. Docker sites can be backed up on demand and on a schedule, and a failed deploy is diagnosed and retried on the same site.
- Pick a Docker server. The agent uses the server you name, or lists your servers and asks. A Docker deploy needs a Docker server; any other stack answers with an incompatible_server refusal, and an agentic server never takes a second site. WordPress is not supported on Docker servers.
- Detect the repository. git_detect reads the repository root for a Dockerfile or one of the four Compose file names, and checks access and server compatibility. It creates nothing, and an access problem is never worked around by naming an app type by hand.
- Scan the Compose file. git_compose-scan runs before the dry run. It lists the services and the host ports the file publishes, resolves which Compose file name it found, and suggests a primary port. The agent never guesses the port.
- Dry run, then one approval. The agent sends the Docker create request with dry_run set to true and shows the resolved configuration: compose file, port, address and warnings. It asks once, naming the server and the URL, before sending the same body with confirm set to true and an idempotency key.
- Poll and verify. A 202 means queued, not running. The agent polls the site status until it is terminal, reads failed_steps and the SSL block, and fetches the URL before it calls the app live. A 502 here usually means the Compose file publishes no port.
- Back up and recover. The agent can take a Docker backup, read the backup list and settings, and add a note to a backup. If a deploy fails it reads the diagnosis, proposes a fix from the correctable fields and retries on the same site after your approval. Restoring a backup is a dashboard step.
Reference
Docker apps Settings and Limits on xCloud
The facts OpenCode works within when it runs Docker apps. Where a row names the dashboard, that step stays yours to take there.
| Setting or limit | What applies |
|---|---|
| Supported inputs | A Dockerfile for a single container, or a Compose file for one or more services, on a Docker server. Go, Python, Rust and Java apps all deploy this way |
| Server stack | Docker servers only. The Docker deploy on any other stack, including an agentic server, answers 422 with the code incompatible_server |
| Which Compose file runs | docker-compose.yml at the repository root. A file named compose.yaml, compose.yml or docker-compose.yaml, or one in a subdirectory, deploys through the pinned Docker create with docker.compose_file set to the path the scan resolved |
| Public port | xCloud's nginx owns ports 80 and 443 and proxies to one host port of 1024 or higher on 127.0.0.1. xCloud runs your Compose file as-is and never rewrites its ports mapping |
| Port refusals | A port another site already holds is refused as port_unavailable. A port the file does not publish is refused as port_not_published, with the published ports listed |
| No published port | A Compose file that publishes no port is accepted and then answers 502, so the scan is the step that catches it |
| Private registries | The deploy runs docker compose pull and never docker login, so an image from a private registry cannot be pulled. Build the image from source instead |
| Environment and redeploys | Send environment values through env_file_content. A redeploy runs git reset --hard and git clean -df in the site directory, so uncommitted server-side changes are lost |
| What a Docker backup holds | Named volumes, eligible bind mounts, the Compose file and the app's .env, in an encrypted snapshot. The app is stopped while the backup captures and restarted afterwards |
| Backup tools | Take a backup, list backups, read the count and the settings, change the settings, add a note and delete a backup. Remote copies go to a storage provider you add in the dashboard |
| Restores | A restore replaces the app's data in place, so it stays a dashboard step: Site, Site Backup, Previous Backups, Restore Backup |
| Dot-prefixed paths | A 403 on a path that starts with a dot is the dot-path allowlist. It is fixed with docker.allowed_dot_paths in the deploy settings, without a rebuild |
Rules OpenCode has to follow
- The Compose file is scanned before the dry run, and the port always comes from the scan, never from a guess.
- A file that binds ports 80 or 443, publishes no port or pulls from a private registry is not deployed as-is. The agent shows the rewrite, such as publishing 127.0.0.1:<high port>:<app port> and building the image from source, and the change goes into your repository.
- Creating a site, deploying, redeploying and deleting a backup stop for your approval. A backup runs without a separate prompt but stops the app while it captures, so ask for one at a quiet time.
- A failed Docker site is retried in place with corrections. It is never deleted and recreated, because it keeps its domain and port.
- Restoring a backup, adding a backup storage provider and changing a live site's domain are dashboard steps; the agent gives you the path and the dashboard link xCloud returned.
Example prompts
What Can You Ask OpenCode to Do for Docker apps?
Type these as written and swap in your own repository, site and server names. Reads and routine actions such as backups, cache purges, PageSpeed scans and vulnerability scans run straight away; creating, deploying, updating, rebooting, deleting, buying or starting a broken-link scan stops and asks first.
Scan docker-compose.yml in this repo and list the services and published ports xCloud would see.Deploy this repo to the Frankfurt Docker server as a Compose app. Dry run first, then ask me.Back up the Docker app on notes.example.com, wait until it completes, then tell me the snapshot time.Scan the docker-compose.yml in github.com/acme/api and tell me which services and ports xCloud would use.Deploy github.com/acme/shop to the Frankfurt Docker server as a Compose app. Scan the compose file first, show me the services and ports, then wait for my approval before creating anything.Deploy the main branch of github.com/acme/api to my Docker server as a Compose app on a staging hostname.My Compose app on notes.example.com answers 502. Check which port its compose file publishes and which port xCloud is using.Take a backup of the Docker app on notes.example.com now, before I upgrade it, and tell me when it is done.Show the backup settings and the last backup of every Docker app on this team, and list the ones with no schedule.The last deploy of the API site failed. Diagnose it, show me the settings I can correct, fix the build command and retry on the same site.OpenCode and Docker apps: Frequently Asked Questions
What people ask before they let OpenCode run Docker apps through xCloud.
Can OpenCode fix my docker-compose.yml before it deploys?
Yes, in your working tree. xCloud runs the Compose file from the repository exactly as committed, so OpenCode edits it, you review the diff, and the change is committed and pushed before the deploy. xCloud never rewrites the ports mapping itself.
Why do I see xcloud_ in front of every Docker tool in OpenCode?
OpenCode prefixes each MCP tool with the name of its server. The same prefix lets you allow or deny the whole xCloud set with a pattern such as xcloud*, which is how you limit the Docker job to one agent.
Which servers can run a Docker app on xCloud?
Docker servers. Node.js, PHP and static builds use Nginx or OpenLiteSpeed servers, and the Docker deploy on any other stack is refused with an incompatible_server code. An OpenClaw, Hermes, Paperclip or DeepSeek Harness server hosts only the site created at provisioning, so it takes no Docker app.
Why does the agent scan the Compose file before deploying?
xCloud proxies to the host port your file publishes and never rewrites it. The scan lists the services and ports, so the agent picks a port that is free on the server and published by the file instead of guessing.
Why does my Compose app answer 502 after it deployed?
The most common cause is a Compose file that publishes no port: xCloud accepts it, then its nginx has nothing to proxy to. Publish the app on 127.0.0.1 with a high port, such as 127.0.0.1:8080:8080, and redeploy.
Can an agent deploy an image from a private registry?
Not as-is. The deploy runs docker compose pull and never docker login, so a private image cannot be pulled. Build the image from source in the Compose file, or deploy a repository that does.
Can an agent back up and restore a Docker app?
It can take a backup, read the backup list and settings, change the settings, add a note and delete a backup. Restoring replaces the app's data in place, so you do that in the dashboard under Site, Site Backup, Previous Backups.
Can I run WordPress as a Docker app on xCloud?
No. Creating a WordPress site on a Docker server is refused because WordPress is not supported on Docker servers. Use an Nginx or OpenLiteSpeed server for WordPress.
Other agents
Docker apps with Other Agents
The same job, the same xCloud tools, a guide for each client.
- Run Docker apps with Claude CodeAnthropic's terminal coding agent. One claude mcp add command, plus the xCloud skills plugin with nine skills on top.
- Run Docker apps with ClaudeAnthropic's chat assistant on the web and desktop. Add xCloud as a custom connector, no terminal needed.
- Run Docker apps with Claude CoworkAnthropic's desktop agent for delegated work. Add the xCloud connector, then hand off hosting jobs.
- Run Docker apps with CursorThe AI code editor. One mcp.json entry with the compact URL, because Cursor stops at 40 tools.
- Run Docker apps with CodexOpenAI's coding agent for the terminal. A codex mcp add command or a config.toml entry, then codex mcp login.
- Run Docker apps with Hermes AgentNous Research's agent with memory and a built-in scheduler. An mcp_servers entry in config.yaml and one login.
- Run Docker apps with OpenClawThe open-source agent runtime with chat apps and automations. ClawHub skill plus the MCP client.
- Run Docker apps with WindsurfThe Cognition editor, now Devin Desktop. devin mcp add for the Devin Local agent, a serverUrl entry for legacy Cascade.
- Run Docker apps with GitHub CopilotCopilot agent mode in VS Code. One .vscode/mcp.json entry, or the Agent Plugins package.
- Run Docker apps with Gemini CLIGoogle's terminal agent. One gemini mcp add command, OAuth found automatically.
- Run Docker apps with ChatGPTOpenAI's chat assistant. A developer-mode app with the xCloud MCP URL and OAuth.
- Run Docker apps with ChatGPT dotsOpenAI's always-on agent in ChatGPT. Uses the xCloud MCP plugin you add in ChatGPT, with custom rules and scheduled tasks.
- Run Docker apps with GrokxAI's terminal agent, Grok Build. One grok mcp add command or a config.toml entry.
- Run Docker apps with Grok BotxAI's always-on Bots on a cloud computer. One Remote HTTPS MCP plugin, OAuth sign-in, routines on a schedule.
- Run Docker apps with KiroAWS's agentic IDE. One url entry in .kiro/settings/mcp.json, plus the portable xCloud Agent Plugins package.
- Run Docker apps with AntigravityGoogle's agentic IDE. One serverUrl entry in mcp_config.json and a browser sign-in.
- Run Docker apps with ZedThe Zed editor's Agent Panel. One context_servers entry in settings.json and a browser sign-in.
More OpenCode guides
- OpenCode and xCloud overview
- Deploy from Git with OpenCode
- Install one-click apps with OpenCode
- Manage WordPress with OpenCode
- Back up and stage sites with OpenCode
- Manage SSL and domains with OpenCode
- Manage servers with OpenCode
- Troubleshoot a broken site with OpenCode
- Speed up a slow site with OpenCode
- Secure sites and servers with OpenCode
Run Your Hosting from OpenCode
xCloud MCP, the Agent Skills and the Public API are free with every account. Connect once and ask.