Screenify Studio MCP server
Commit Oct 28, 2026Lets an AI assistant record screens, apply cinematic styles, and export professional demo videos locally on macOS.
Also known as ScreenifyStudio/screenify-mcp, screenify-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 2.2.1
- Last commit
- Oct 28, 2026
- License
- MIT
What is Screenify Studio MCP?
Screenify Studio lets an AI assistant record screens, apply cinematic styles, and export professional demo videos locally on macOS.
Summary generated from the project's README
About Screenify Studio MCP server
Creating professional demo videos through an AI assistant is what Screenify Studio enables for macOS users. While other servers allow an AI to view your screen, this tool allows Claude, Claude Code, or Cursor to actually record, style, and export video files. It functions as a local bridge to the Screenify Studio application, utilizing the CLI included in version 2.2.0 or newer to process tasks without uploading data to the cloud.
Users can manage the entire production pipeline by requesting specific outputs like mp4, mov, gif, or webp files. The server handles recording various targets including windows, specific areas, simulators, or web pages. It also applies cinematic effects, device mockups, auto-zoom, and animated titles to the footage. Setup is handled via a one-click bundle for Claude Desktop, a plugin for Claude Code, or by using the internal settings menu within the Screenify Studio app to register the server with any local MCP client.
What you can do with it
- 1Generate styled product demosAsk your AI assistant to record a specific landing page and place it inside a professional café desk mockup.
- 2Create cinematic software walkthroughsInstruct an AI to record a window and apply camera moves or cinematic effects to highlight important moments.
- 3Convert existing media into styled videosProvide an existing image or video to the AI and have it apply new styles and mockups.
- 4Automate multi-format video exportsRequest a screen recording to be exported specifically as a gif or webp file using platform presets.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablescreenifystudio/screenify-mcp is public and reachablegithub.com/screenifystudio/screenify-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-28github.com/screenifystudio/screenify-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubScreenify Studio — MCP server
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.
What it can do
Connect it to an AI assistant and ask for the finished video instead of driving the editor yourself:
- record a screen, window, area, simulator or a web page
- style the export — wallpapers, device mockups, photo mockups, auto-zoom, cinematic effects
- add camera moves and effects to the moments that matter
- add animated titles — and keep the ones you made in the app when exporting
- open a video or image you already have and style that instead
- export to mp4, mov, gif or webp, with platform presets
Everything runs locally on your Mac. Nothing is uploaded.
Install
Requires Screenify Studio 2.2.0 or newer. The bundle carries no binary — it launches the CLI that ships inside the app.
Claude Code and Cowork — plugin
This repository is also a Claude plugin. It bundles the MCP server with a skill that teaches Claude which Screenify flow to use for a request. In Claude Code:
claude --plugin-dir /path/to/screenify-mcp
The plugin's server runs locally, so it works in Claude Code and in Cowork sessions on your Mac. In a regular Claude chat, use the one-click bundle below instead.
What the plugin runs. scripts/screenify-mcp.sh looks for the screenify command that ships
inside the Screenify Studio app (/Applications/Screenify Studio.app, or the copy the app installs
at ~/.screenify/bin) and starts it as an MCP server over stdio. It downloads and installs nothing.
If the app is missing, it returns an error that tells you where to get it.
Claude Desktop — one click
Download screenify.mcpb
and open it. Claude Desktop installs the connector.
Any other MCP client
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 mcp install
From a registry
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.
Docs
Privacy Policy
Full policy: www.screenify.studio/privacy
In short, for this MCP server specifically:
- What it collects — nothing. The server runs locally on your Mac and exposes tools to an MCP client you already trust. It has no telemetry of its own.
- Where your data goes — recordings, projects and exported videos stay on your Mac, in your recordings folder and wherever you ask for the output. Nothing is uploaded by the server.
- Third parties — none for the recording and export tools. Two features reach out only when you explicitly use them: web recording fetches the URL you ask for, and the optional AI-director effects call the AI provider whose API key you supplied.
- Retention — the server keeps nothing after a job finishes; the files it produced are yours to keep or delete.
- Contact — support@screenify.studio
Support
Issues with the MCP server or the app: support@screenify.studio
License
This repository — the Claude plugin (a manifest, a launcher script and a skill), 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.
Screenify Studio MCP questions
Does my data get uploaded to the cloud?
No, everything runs locally on your Mac and nothing is uploaded by the server.
What video formats can I export?
You can export your videos to mp4, mov, gif, or webp using platform presets.
Does the MCP server collect any telemetry?
The server has no telemetry of its own and collects nothing, as it runs locally on your Mac.