The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Screenify Studio listing page.
Every other screen-related MCP server lets an AI look at your screen. This one lets it make a video.
Ask Claude, Claude Code or Cursor for a demo and get back a finished file — recorded, styled and exported. No terminal, no flags, no editor.
"Record a 12-second demo of my landing page and put it on a café desk mockup."
Everything runs locally on your Mac. Nothing is uploaded.
https://github.com/user-attachments/assets/8c753dcb-0e53-4c00-acd6-0cd934b19415
Asked in a chat window; recorded, styled and exported by Screenify. No editor was opened.
Connect it to an AI assistant and ask for the finished video instead of driving the editor yourself:
Everything runs locally on your Mac. Nothing is uploaded.
Requires Screenify Studio 2.2.0 or newer. The bundle carries no binary — it launches the CLI that ships inside the app.
Download screenify.mcpb
and open it. Claude Desktop installs the connector.
Open Screenify Studio → Settings → AI Assistants → Connect AI assistants. It registers the server with every AI client it finds on your Mac. Or from a terminal:
Screenify is listed in the official MCP registry
as studio.screenify/screenify, so clients that read the registry can find and install it
without any of the steps above.
Full policy: https://www.screenify.studio/privacy
In short, for this MCP server specifically:
Issues with the MCP server or the app: support@screenify.studio
This repository — the MCP bundle (screenify.mcpb: a manifest, a launcher script and an icon)
and its documentation — is MIT licensed.
Screenify Studio itself is proprietary software and is not covered by that license. The app provides the MCP server, the recording pipeline and the export engine; this repo only ships the small bundle that launches it.