AI Video Enhancer Studio

com.contenta-softwarev1.0.0Updated Oct 2, 2026

Upscale, stabilize, denoise and raise the frame rate of videos locally on your NVIDIA GPU

VerifiedSTDIODesktop onlyAI & ML Media & Design

Overview

AI-generated overview

Lets an assistant run local NVIDIA-GPU video enhancement on Windows: upscaling, stabilization, denoising and frame-rate conversion.

What it does: A small launcher that finds the AI Video Enhancer Studio desktop app on a Windows PC and runs the app's own MCP server over stdio. It exposes tools named enhance_video, analyze_video, get_status and list_presets for upscaling, stabilizing, denoising and frame-rate conversion of local video files. If the app is not installed, the launcher instead serves a single get_started tool that returns the download link and install steps.
When to use it: Worth adding when you want an assistant to process video files already on a Windows machine with an NVIDIA RTX GPU, for example batch upscaling or frame-rate conversion driven from Claude Code, Cursor, VS Code or Codex. Not useful on macOS, Linux or machines without a supported GPU.
Requirements: Windows 10/11 desktop with an NVIDIA RTX GPU, Node.js/npx for the launcher package, and the AI Video Enhancer Studio app installed (aivideoenhancer.exe in %LOCALAPPDATA%\Programs\AIVideoEnhancerStudio or on PATH). No API keys or environment variables are declared. Long encodes may need a raised client startup and tool timeout.

Before you install

The app sends anonymous usage telemetry (tools run, MCP client, trial state) to ContentaSoft and can be turned off in the app's settings. During the trial some output is watermarked or limited; after the trial, tools that write files return a purchase link instead of running. Jobs write output files on the local machine and are stopped when the client cancels.

Installation

In SourceWeft

Open AI Video Enhancer Studio in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AI Video Enhancer Studio MCP server

Lets an AI agent (Claude Code, Claude Desktop/Cowork, Codex, Cursor, VS Code and other MCP clients) use AI Video Enhancer Studio on your Windows PC: upscaling, stabilizing, denoising and frame-rate conversion of videos on an NVIDIA RTX GPU.

AI Video Enhancer Studio is a Windows 10/11 desktop app with a free trial: https://www.contenta-software.com/aivideoenhancer/download.php

How it works

This package is a small launcher. It finds AI Video Enhancer Studio on your PC (aivideoenhancer.exe, installed per-user in %LOCALAPPDATA%\Programs\AIVideoEnhancerStudio or on your PATH) and runs the app's own MCP server (aivideoenhancer serve) over stdio. Tools: enhance_video, analyze_video, get_status, list_presets.

If the app is not installed yet, the launcher serves a single get_started tool that gives your agent the download link and the install steps instead.

Add it to your client

Claude Code (Windows):

Claude Desktop, Cursor and other clients that use mcpServers (JSON):

json

{  "mcpServers": {    "ai-video-enhancer": { "command": "cmd", "args": ["/c", "npx", "-y", "@contentasoft/[email protected]"] }  }}

{  "mcpServers": {    "ai-video-enhancer": { "command": "cmd", "args": ["/c", "npx", "-y", "@contentasoft/[email protected]"] }  }}

VS Code (.vscode/mcp.json, note the servers key):

json

{  "servers": {    "ai-video-enhancer": { "type": "stdio", "command": "cmd", "args": ["/c", "npx", "-y", "@contentasoft/[email protected]"] }  }}

{  "servers": {    "ai-video-enhancer": { "type": "stdio", "command": "cmd", "args": ["/c", "npx", "-y", "@contentasoft/[email protected]"] }  }}

Codex (codex mcp add ai-video-enhancer -- cmd /c npx -y @contentasoft/[email protected], or ~/.codex/config.toml):

toml

[mcp_servers.ai-video-enhancer]command = "cmd"args = ["/c", "npx", "-y", "@contentasoft/[email protected]"]startup_timeout_sec = 60tool_timeout_sec = 3600

[mcp_servers.ai-video-enhancer]command = "cmd"args = ["/c", "npx", "-y", "@contentasoft/[email protected]"]startup_timeout_sec = 60tool_timeout_sec = 3600

The first start downloads this small package, which can take longer than a client's default startup timeout (Codex: 10 s; Claude Code: set MCP_TIMEOUT); after that it starts at once. Long jobs such as video encodes can exceed a client's default tool timeout too (Codex: 60 s; Claude Code: MCP_TOOL_TIMEOUT). The app is told to stop a job when the client cancels it.

Once the app is installed you can also skip the launcher: "command": "aivideoenhancer", "args": ["serve"].

What runs and what is sent

The launcher itself sends nothing over the network and writes nothing to disk. It starts aivideoenhancer.exe.
The app works on local files on your PC. It sends anonymous usage telemetry (which tools ran, which MCP client connected, trial state) to ContentaSoft; turn it off in the app's settings. Privacy policy: https://www.contenta-software.com/aivideoenhancer/privacy.php
During the trial some output is watermarked or limited; after the trial, tools that write files answer with a link to buy a license instead of running.

License

The launcher is MIT-licensed (see LICENSE). AI Video Enhancer Studio itself is commercial software by ContentaSoft AB.

Source: packages/ai-video-enhancer-mcp/README.md at commit 06876ad

Tools

Tool metadata has not been indexed yet.

Version history

v1.0.0LatestOct 2, 2026