The MCP server for your deployments

Connect your AI coding assistant to Ploi Cloud once. From then on, deploying is just describing what you need.

terminal
$
AI:
bash
bash
applications_store
application_services_store
application_services_store
applications_deploy
Your app is live at https://my-saas-app.ams.preview.ploi.it
MySQL and Redis credentials were injected automatically.

The Model Context Protocol (MCP) is the open standard that lets AI tools talk to services like Ploi Cloud. Our hosted MCP server exposes the whole platform — deployments, databases, domains, logs, environment variables — as tools your AI assistant can use on your behalf.

There is nothing to install or self-host. Point your MCP client at ploi.cloud/mcp, authorize once in your browser, and every capability of the platform becomes available in plain language.

How it works

Three steps from your editor to a live application

  1. 1

    Connect

    Add Ploi Cloud to your AI tool's settings. Sign in once to authorize access.

  2. 2

    Describe

    Tell your AI what to deploy. "Deploy my Laravel app with a database" is all it takes.

  3. 3

    Live

    Your app is deployed, configured, and running with automatic SSL. In under a minute.

Connect in one command

Run this in your terminal and you're ready to go

Claude Code

$ claude mcp add --transport http ploi-cloud https://ploi.cloud/mcp

Cursor, Windsurf, or any MCP client

URL: https://ploi.cloud/mcp

Your browser will open once to authorize access. That's all the setup there is.

What you can do

Everything you need, through natural language

Deploy applications

Deploy from your git repository with automatic framework detection and configuration.

Add databases and caches

MySQL, PostgreSQL, Redis, MongoDB, and more. Added with a single sentence.

View logs and debug

Check application logs, deployment output, and debug issues without leaving your editor.

Manage environment variables

Add, update, and manage secrets securely. Service credentials are injected automatically.

Custom domains with SSL

Add your own domain and get automatic SSL certificates. Zero configuration needed.

Monitor deployments

Track deployment progress in real-time. Get notified of issues and auto-fix common failures.

Supported tools

Works with any AI tool that supports the Model Context Protocol

Claude Code

Anthropic's CLI agent

Claude Desktop

Desktop AI assistant

Cursor

AI-powered editor

Windsurf

AI-powered IDE

VS Code + Copilot

With MCP support

Any MCP client

Open protocol

Frequently asked questions

Everything you need to know about the Ploi Cloud MCP server

What is the Ploi Cloud MCP server?

It is a hosted Model Context Protocol server at https://ploi.cloud/mcp that exposes the Ploi Cloud platform as tools for AI assistants. Once connected, tools like Claude Code or Cursor can deploy applications, add databases, manage domains, and read logs on your behalf.

How do I connect Claude Code to Ploi Cloud?

Run "claude mcp add --transport http ploi-cloud https://ploi.cloud/mcp" in your terminal. Your browser opens once to authorize access, and after that Claude Code can manage your applications directly.

Which AI tools work with the MCP server?

Any client that supports the Model Context Protocol: Claude Code, Claude Desktop, Cursor, Windsurf, VS Code with Copilot, and others. If your tool can add an MCP server by URL, it works with Ploi Cloud.

Is the MCP connection secure?

Yes. Authentication uses OAuth 2.1, the same standard used for the Ploi Cloud API. You authorize the connection once in your browser, and you can revoke access at any time from your account settings.

Do I need to install or host anything?

No. The MCP server is fully hosted by Ploi Cloud. You only add its URL to your AI tool — there are no packages to install, no processes to run, and nothing to keep updated.

What can the AI actually do through MCP?

Everything the Ploi Cloud API can do: create and deploy applications, provision databases and caches, manage environment variables, add custom domains with SSL, monitor deployments, and read logs. The tools are generated from the same API that powers the dashboard.

Ready to try it?

Create a free account and connect your AI tool in under a minute. The setup guide walks you through every step.