Deploy From Claude Code, Cursor, or Codex
Your MapleDeploy server has an MCP endpoint built in. Turn it on, and your AI coding client can deploy your apps, restart services, and read logs on your own server in Toronto.
The Model Context Protocol (MCP) is how AI clients like Claude Code, Cursor, and Codex connect to outside tools. The endpoint lives at /mcp on your server, part of the Coolify install your plan already includes. There are no scripts to write, no third-party wrapper to trust, and nothing extra to host.
What your AI client can do once it's on:
Deploy and redeploy
Ask for a deploy after a change. The client queues the same deployment you would start by hand.
Start, stop, restart
Start, stop, or restart an app, database, or service without opening a dashboard.
Read logs
Pull recent logs into the conversation, so the client can help you debug what just broke.
Limited by its token
The API token you give the client sets its limits. A read token can look around. A deploy token can act.
How it works
- 1
Turn it on
In the MapleDeploy dashboard, open your server's Tools tab and turn on the MCP server. You see exactly what it exposes before you confirm.
- 2
Create an API token
In Coolify, go to Security, then API Tokens, and create a token with only the abilities your client needs. The token signs the client in and limits what it can do.
- 3
Connect your client
Add your server's /mcp endpoint and your token to Claude Code, Cursor, or Codex. Then ask it to deploy.
What it exposes
Once it is on, any Coolify API token on your instance can reach the endpoint, including read-only tokens. Keep each token's abilities as narrow as the job needs.
The realistic risk is prompt injection: text your client reads that tries to steer what it does next. The endpoint never returns environment variable values, only their names. You can turn it off at any time from the same dashboard setting, and the setup guide covers token abilities in detail.
On Canadian infrastructure
Your server, its Coolify instance, and the MCP endpoint all run on a dedicated VM in Toronto. Deploys run there, and your application data stays there, governed by Canadian privacy law rather than the US CLOUD Act.
Anything your client reads through the endpoint, such as logs, becomes part of its conversation with its AI provider, like the code you write with it. Choose token abilities with that in mind.
The endpoint uses your server's existing HTTPS address, so there is no new port to open. It stays off until you turn it on.
Built on open source
The MCP server is not a MapleDeploy add-on. It ships with Coolify, the open-source platform your server runs, so you can read exactly how the endpoint and each of its tools behave in the source.
If an AI client helped you build the project, this closes the loop: the same client that wrote your code can now deploy it, on infrastructure you control.
Ready to deploy with your AI client?
30 days free on Starter and Pro. Start a server, turn on the MCP server, and deploy a real project from Claude Code, Cursor, or Codex. The setup guide walks you through connecting your client.