MCP server · Video editing · official

OpenScreen MCP server

Let your AI record your screen, edit the video, and export a finished demo clip for you.

OpenScreen is a free desktop app for recording your screen and turning the recording into a clean demo or walkthrough video. This MCP server is the part that lets your AI assistant drive the app for you. It is handy if you make product demos, tutorials, or bug-report videos and would rather describe what you want than click through an editor.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program that gives your AI a new skill or a connection to an app, and here that app is OpenScreen on your own computer. Once it is connected, your AI can ask OpenScreen to start a recording, make edits to the video, and export the result. You still talk to your AI in plain words; the helper does the clicking behind the scenes.

What this MCP server does

You tell your AI what video you want, for example a short demo of a feature. The AI uses this helper to open OpenScreen and record your screen for the length you asked. Then it edits the recording: trimming the boring parts, adding zooms, captions, or annotations. Finally it exports the video as an MP4 or GIF file and can hand it back to you or attach it to a pull request. You watch the result and ask for changes if something is off.

What you can do with it

Record your screen or a single window for a set number of seconds
Trim the start and end of a recording and cut out dead time
Add zooms that follow your cursor or land on a spot you pick
Add captions from your voiceover, transcribed on your own machine
Add text, arrows, and image annotations to the video
Export the finished video as MP4 or GIF in different sizes
Attach the exported video to a pull request for reviewers

Try asking your AI

“Record a 30 second demo of the settings page and export it as an MP4”
“Make a demo video of this feature and attach it to my pull request”
“Trim the first ten seconds off demo.openscreen and add a zoom on the save button”
“Export the project as a GIF at 800 pixels wide for the docs page”

What it gives back to you

You get back short status messages in the chat, like confirmation that a recording finished or an export completed. When it exports, it gives you the path to the video file, and your AI can attach that file to a pull request or show you where it is. If it reads a project, it can tell you what is on the timeline, such as the clips, zooms, and annotations. The actual video is a normal file on your computer that you can open and watch.

Before you start

What you need

The OpenScreen desktop app installed on your computer
The path to the OpenScreen executable on your system
Screen Recording and Accessibility permissions granted to OpenScreen (macOS)
An AI client that supports MCP, such as Claude Code or Codex

Good to know

It records your screen and can change or export video files on your computer, so check what it captured before you share it.

Install it with your AI

Add OpenScreen MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check OpenScreen MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.