Zed + xCloud

Deploy from Git with Zed on xCloud

Deploying from Git with Zed means asking the Agent Panel in the Zed editor to ship the project you have open, and letting xCloud detect the app, preview the site, create it after your approval and verify the live URL.

Skill: xcloud:deploy
Toolsets: sites, servers, integrations
Free with every xCloud account

Set up Zed All Zed guides

YouUse xCloud to deploy this repository to Frankfurt on a staging hostname. Dry run first.

git_detectread-only

AgentNode.js app on main, build npm run build, start npm start. Staging address: site-staging.acme.xcloud.site. No .env in the repo. Create it?

YouYes.

servers_sites_git_autoneeds approval

AgentDeployed. https://site-staging.acme.xcloud.site answers 200. Dashboard link below.

Last updated: October 2026. 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 Zed to Deploy from Git on xCloud?

Connect Zed once; every job on this account uses the same connection. Then ask in plain words.

1
Add xCloud as a remote server
Open Settings, then AI, then MCP Servers, click Add Server and choose Add Remote Server. Or run the zed: open settings file action and add this to settings.json yourself. Zed writes the same entry either way.
JSON
```
{
  "context_servers": {
    "xcloud": {
      "url": "https://app.xcloud.host/mcp"
    }
  }
}
```
2
Sign in and check the dot
Because the entry has no Authorization header, Zed prompts you to authenticate through the MCP OAuth flow. Approve the teams and the access level in the browser. In Settings, AI, MCP Servers a green dot next to xcloud with the tooltip Server is active means it worked. Then ask this in the Agent Panel.
Prompt
```
Who am I on xCloud?
```
3
No browser sign-in? Use an API key
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 add it as a header. With an Authorization header set, Zed skips its OAuth prompt. Replace YOUR_TOKEN with the token, which contains a pipe character, and keep it out of git and out of chat.
JSON
```
{
  "context_servers": {
    "xcloud": {
      "url": "https://app.xcloud.host/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}
```

Check it worked

Then ask Zed for the job itself, for example:

Prompt

Use xCloud to deploy this repository to my Frankfurt server on a staging hostname and show me the dry run first.

In practice

How Does Deploy from Git Work from Zed?

Zed's Agent Panel opens beside the buffer you are editing, so a deploy is a request typed into the panel while the project is still in front of you. Zed notes that how reliably MCP tools get called varies by model, and naming the server helps the model pick the right tools, so write the request as Use xCloud to deploy this repository to my Frankfurt server on a staging hostname. The agent then calls git_detect and reports the app type, the branch, the commands xCloud would run and any warning, and Zed shows each tool call in the panel as it happens, so you can see which calls only read and which would change something.

Zed's own permission setting gives you a second checkpoint. With agent.tool_permissions.default left on confirm, each MCP tool call asks first, and for per-tool rules the key format is mcp:xcloud:<tool_name>, for example mcp:xcloud:git_detect for the detection call. A reasonable arrangement for this job is to relax the read calls and keep the create call, servers_sites_git_auto, on confirm. After the dry run summary you approve once, Zed asks, xCloud requires its explicit confirmation, and the agent polls sites_status and reports each real step change. It fetches the URL and reads failed_steps before it says the site is live.

Zed can also forward the servers you configure to External Agents, so if you run another agent through the Agent Client Protocol in the same editor, the xcloud entry is available to it too. For a failed build the loop is the usual one: read the deployment diagnosis, adjust a build script or the xCloud build command, and retry on the same site after you approve. The status dot in Settings, AI, MCP Servers is the quickest check before you start, since green with the tooltip Server is active means a deploy request has tools to call.

Zed specific: Name xCloud in the prompt. A bare line like ship this repo can be read as a request to push to a remote or run a local command, while Use xCloud to deploy it points the model at the xcloud tools. Also check your Zed version: the approval setting is agent.tool_permissions.default from v0.224.0, and older versions used agent.always_allow_tool_actions. If you have relaxed approval for convenience, set it back to confirm before a deploy, so the prompt still appears ahead of the create call.

What xCloud does for deploy from git

xCloud detects the app in the repository, previews the site it would create with a dry run, creates it once you approve, polls the deployment to a terminal state and checks the live URL. A failed deploy gets a diagnosis and a corrected retry on the same site, never a delete and recreate.

Pick the team and server. The agent uses the server you name. If you name none it lists provisioned servers and asks; it never picks one silently. Node.js, PHP and static builds need an Nginx or OpenLiteSpeed server; anything else needs a Docker server.
Detect the repository. git_detect reads the default branch, the app type (WordPress, Laravel, custom PHP, Node.js or Lovable), the web root, suggested install, build and start commands, repository access and server compatibility. Detection creates nothing.
Choose the address. With no domain the agent asks xCloud for a free staging hostname. With a live domain it checks whether the zone is on a connected Cloudflare account, in which case xCloud writes the DNS record and certificate itself.
Dry run, then one approval. The agent sends the create request with dry_run set to true and shows you the resolved configuration: app type, URL, branch, commands, runtime version and every warning. Then 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 deployed. The agent polls the site status until it is terminal, reports each real step change, reads failed_steps and the SSL block, and fetches the URL before it calls the site live.
Recover if it fails. On a failed deploy the agent reads the deployment diagnosis, proposes a fix from the correctable fields, and retries on the same site with your approval. Two failed retries with the same classification stop the loop and hand you the dashboard link.

Reference

Deploy from Git Settings and Limits on xCloud

The facts Zed works within when it deploys from Git. Where a row names the dashboard, that step stays yours to take there.

Setting or limit	What applies
Supported app types	WordPress, Laravel, custom PHP, Node.js and Lovable on native servers; Dockerfile and Compose apps, including Python, Go and Rust, on Docker servers
Repository sources	Public HTTPS URLs, repositories on a connected GitHub, GitLab or Bitbucket provider, and private SSH repositories with a read-only deploy key
Private repositories	The agent prepares a deploy key on the server, you add the public key to the repository, xCloud verifies it. A private key or personal token never goes in the request
Preview	dry_run: true returns the would_create block and consumes no idempotency key
Idempotency	The create call carries an Idempotency-Key, so a retried request cannot create a duplicate site. A new deployment needs a new key
Deployment states	deployed, failed or cancelled once terminal is true; failed_steps can be non-empty on a deployed site and must be read
Node.js versions	The Node version is server-wide, not per site; changing it can affect other apps on the server
Redeploys	A redeploy runs git reset --hard and git clean -df in the site directory, so uncommitted server-side changes are lost. Supply environment values through env_file_content, not files in the checkout
Staging environments	Available for Git sites on paid plans through the API; WordPress staging stays a dashboard step
Agentic servers	An OpenClaw, Hermes, Paperclip or DeepSeek Harness server hosts only the site created at provisioning; a second site is refused

Rules Zed has to follow

Creating a site is billable and stops for your approval; detection and the dry run never create anything.
The agent explains every detection warning before asking, and a repository access problem is never worked around by naming an app type by hand.
A deployed state is not proof the application works: the agent fetches the URL and reads failed_steps first.
A failed site is retried in place with corrections; it is never deleted and recreated to retry.
Changing a live site's domain after creation, databases and server resizing are dashboard steps; the agent gives you the path and the dashboard link xCloud returned.

Example prompts

What Can You Ask Zed to Do for Deploy from Git?

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.

Prompt

Use xCloud to deploy this repository to my Frankfurt server on a staging hostname and show me the dry run first.

Prompt

Use xCloud to run detection on this project and tell me the build command, start command and any warning. Create nothing.

Prompt

Use xCloud to read the diagnosis for the failed deploy of this project and tell me which file I should change.

Prompt

Deploy https://github.com/acme/shop to my Frankfurt server and show me the dry run before creating anything.

Prompt

Deploy the private GitLab repository connected to my team on a staging hostname.

Prompt

Scan the docker-compose.yml in github.com/acme/api and tell me which services and ports xCloud would use.

Prompt

Create a staging environment from the feature/checkout branch of the API site.

Prompt

Deploy the latest commit of the shop site after showing me what will change.

Prompt

The last deploy of the API site failed. Diagnose it, fix the build command and retry on the same site.

Zed and Deploy from Git: Frequently Asked Questions

What people ask before they let Zed deploy from Git through xCloud.

Why should I write Use xCloud to in Zed when I deploy?

Zed notes that how reliably MCP tools get called varies by model, and naming the server helps the model choose them. A request that starts with Use xCloud to deploy points the agent at the xcloud tools rather than at your shell.

How do I stop Zed from approving the xCloud create call on its own?

Leave agent.tool_permissions.default on confirm, or write a per-tool rule keyed mcp:xcloud: followed by the tool name, and relax only the read tools. xCloud also refuses the create call without an explicit confirmation, so the site is never created without your yes.

Does the agent create the site as soon as I give it a repository URL?

No. It detects the repository and runs a dry run first, shows you the resolved configuration, and asks once. Only after you approve does it send the create call with an explicit confirmation and an idempotency key.

Can an agent deploy a private repository through xCloud?

Yes. Either the repository is on a Git provider connected to your xCloud team, or the agent prepares an SSH deploy key on the server for you to add to the repository. A private key or a personal access token is never sent in the request.

What does a 202 response mean during a deploy?

That xCloud queued the deployment. The agent polls the site status until it is terminal and reports deployed, failed or cancelled, then checks failed_steps and fetches the URL before calling the site live.

What happens when a deploy fails?

The agent reads the deployment diagnosis, which classifies the failing step and quotes the relevant log lines, proposes a fix from the fields xCloud lets it correct, and retries on the same site after your approval. It never deletes and recreates the site to retry.

Which servers can take a Git deploy?

Node.js, PHP and static builds deploy to Nginx or OpenLiteSpeed servers. Dockerfile and Compose apps, and other language stacks, need a Docker server. Agentic servers running OpenClaw, Hermes, Paperclip or DeepSeek Harness take no additional sites.

Other agents