Use cases · MCPENROUZ

Remote development with AI through MCP

Your editor and AI client can run on one machine while the project lives on another. MCPENROUZ exposes tools on the selected device without moving the project into chat.

Free2 devices · 100 tool calls per hour
Example task
On Development server, inspect /srv/app, read its instructions, check git status and propose a fix for the sign-in issue.
Your device · your permissions
01

Existing project

Use the existing repository, branch and dependencies on the development machine.

02

Inspect first

Read the README, project instructions and code map before the first edit.

03

Verify in the same environment

Run relevant tests where the result will be used.

Get started

  1. Connect the development machine

    Select the working directory. Start with reads, then add writes and terminal access for the task.

  2. Confirm device and branch

    Name the device, directory and expected branch. Ask for a repository status check.

  3. Implement and verify

    Review the plan, make focused changes and inspect verification results.

Example task

A prompt for your AI
On Development server, inspect /srv/app, read its instructions, check git status and propose a fix for the sign-in issue.

Permissions

Reads, writes and shell are separate permissions. Git and dependency commands need terminal access.

Details

Isolate working changes

Use a separate branch or worktree for an independent task. Check uncommitted changes before starting.

Publishing the result

Committing, pushing and deploying are separate actions. Specify which are authorized for the task.

Frequently asked questions

Do I need to copy the project to my laptop?

No. Tools work with the project on the selected connected device.

Does it work with Cursor and Claude Code?

Yes, through remote MCP and OAuth. Each has a dedicated setup guide.

What if the machine disconnects?

Check the agent and network. Do not treat an edit or test as complete without its actual result.

Next steps

MCPENROUZ · FREE

Connect a device. Start with reads.

Choose a working folder and AI client. Add writes and terminal access as your task requires.