Skip to content

CLI, skill, or MCP ​

Agents reach ZynoHosting through one of two interfaces. Use the CLI with the ZynoHosting skill wherever the agent has a shell. Use the MCP server only where it doesn't: the Claude desktop app.

ClientUseWhy
Claude Code (terminal, IDE, desktop Code tab), CodexCLI + skillHas a shell. Nothing runs or loads until a task needs it.
Muse Code, Cursor, and other local coding agentsCLI + skillSame as above.
Grok Bot, ChatGPT dotsCLI + skill, run on their cloud computerSign-in is a link and code the user approves anywhere.
Claude desktop app, Chat and Cowork tabsDesktop extension (.mcpb, the MCP server)No shell, so a CLI is unusable there.
CI and scriptsCLI with ZYNOHOSTING_DEPLOY_TOKENNo agent involved. A deploy token deploys one site only.

Why the CLI is the default for coding agents ​

An MCP server is configured per project and starts with every agent session. It spawns npx at startup and adds over twenty tool schemas and its instructions to the agent's context, even in sessions that never touch hosting. Adding one also requires restarting the agent and approving the server.

A skill costs a one-line description until the agent decides it is relevant, then loads its instructions. The CLI runs only when invoked. The agent can install the skill and use it in the same session, so there is no restart.

The CLI already has what an agent needs:

  • the same operations as the MCP tools: sites, files, deploy, preview, promote, download, and ZynoForms (zynohosting forms …, JSON in and out, with the same inputs and results as the MCP form tools);
  • --json with stable error codes and exit codes;
  • --dry-run for deploy, promote, and sites set;
  • a non-interactive guard: deploy, promote, sites set, download, and files rm exit with confirmation_required instead of prompting when --yes (or --dry-run) is missing. files put applies immediately, so the skill tells agents to get approval first.

The policy the MCP server delivers as server instructions, such as never guessing a domain or never forcing a promotion, lives in the skill instead.

Why the MCP server stays ​

The Claude desktop app's Chat and Cowork tabs cannot run a CLI. They are the main non-technical audience, and the signed desktop extension is their only way in. It needs no Node.js install and updates itself.

For Codex and Claude Code, the project-level MCP setup (mcp install) is now optional. Use it only when a team prefers MCP tools to shell commands.

What the CLI does not do that the MCP server does ​

MCP behaviorCLI equivalent
plan_deploy returns a planId; apply_deploy applies exactly that plan.deploy --dry-run shows a plan; deploy --yes plans again and applies at once. The agent re-runs the dry run if anything changed.
login returns the one-time URL, or a link and code, as a tool result.login opens the browser and blocks for up to 300 seconds. Where no browser can open it shows a link and code. For shells that show output only when a command exits, the agent runs login --device --no-wait --json, then login --resume --json.
list_logins, use_login, and a tenant input on every tool.logins, logins use, and --tenant (or ZYNOHOSTING_TENANT).
Local roots (--root, ZYNOHOSTING_MCP_ROOTS) confine local paths.None. The agent's own permission system governs the shell.

Possible follow-ups ​

These would close the remaining gaps between the CLI and the MCP server:

  1. A plan file for deploy and promote (for example --plan-out/--plan-in), so an approved dry run is exactly what gets applied.
  2. A zynohosting skill install --agent claude|codex command, so the skill ships in the npm package and stays version-matched to the CLI.

Where the guidance lives ​

InterfaceAgent guidance
CLIskills/zynohosting/SKILL.md, installed by install.md
MCPSERVER_INSTRUCTIONS and tool descriptions in src/mcp/server.ts and src/mcp/forms.ts, delivered on every connection

Keep both in step when behavior changes. The preview guide is the shared reference for the preview model.

Documentation for the ZynoHosting CLI and local MCP server.