Automate AI Video Enhancement: CLI, MCP Server, and Claude Code Skill

July 2, 2026 • ContentaSoft Team

Most people meet AI Video Enhancer Studio through its Windows wizard: load a video, pick an enhancement preset, click Start. But the wizard is only one way to drive it. The same engine — NVIDIA RTX Video Super Resolution upscaling, RIFE frame interpolation, denoising and stabilization — also ships with a full command-line interface called aivideoenhancer, a built-in MCP server, and an installable Claude Code skill.

This post walks through all three: enhancing videos from the aivideoenhancer CLI, wiring the MCP server into Claude Desktop or Claude Code, and letting an AI agent run your enhancement pipeline from plain English. The CLI has no --json flag — for AI agents, use the MCP server instead. Full CLI and MCP reference lives in the public GitHub repository at https://github.com/brunojanvier77/ContentaSoft.

The aivideoenhancer CLI: the same engine, scriptable

The executable is called aivideoenhancer and installs together with the desktop app — same installer, same license. You will find it in C:\Program Files\ContentaSoft\AI Video Enhancer Studio\; add that folder to your PATH and it is available from any terminal.

Start with status to check GPU availability and license state, then analyze to inspect a file before you commit to a long enhancement run:

aivideoenhancer status
aivideoenhancer analyze video.mp4

A single enhance command applies upscaling, denoising, and stabilization in one pass:

aivideoenhancer enhance old_tape.mp4 --output ./enhanced --upscale x4 --denoise strong

Batch enhancement: entire folders unattended

Point enhance at a folder and pick a preset — old tape restoration, anime upscaling, or low-light cleanup:

aivideoenhancer enhance ./family-videos --output ./restored --preset old_video_restoration

The engine processes files one after another on your GPU and writes the results to the output folder. Wrap it in a scheduled task and your archive converts overnight, with no per-minute billing.

The MCP server: the right interface for AI agents

MCP (Model Context Protocol) is the open standard AI assistants use to call external tools. Because the CLI has no --json mode, the MCP server is the intended path for AI agents — you start it with one command:

aivideoenhancer serve

Add this to your claude_desktop_config.json to connect Claude Desktop:

{
  "mcpServers": {
    "aivideoenhancer": {
      "command": "C:\\Program Files\\ContentaSoft\\AI Video Enhancer Studio\\aivideoenhancer.exe",
      "args": ["serve"]
    }
  }
}

From then on you can ask things like “enhance every MP4 in my Downloads folder with the old video restoration preset” and the agent calls the local engine directly.

Claude Code skill: video enhancement in plain English

If you use Claude Code, install the /contenta-video-enhancer skill — it teaches the agent the CLI commands, presets, GPU requirements, and common recipes:

git clone https://github.com/brunojanvier77/ContentaSoft
cp -r ContentaSoft/skills/* ~/.claude/skills/

Then describe the job in your own words — “upscale this wedding folder to 4K with strong denoising” or “analyze this clip and suggest the best preset”. The skill builds the right aivideoenhancer commands and reports back.

Everything is documented on GitHub

The complete reference lives in a public GitHub repository: accurate CLI documentation for every command and option, the full MCP server reference, and installable Claude Code skills for AI Video Enhancer Studio and the other ContentaSoft products — https://github.com/brunojanvier77/ContentaSoft.

GPU requirements: NVIDIA RTX for VSR

Most enhancement modes run on any modern GPU via DirectML or CUDA. NVIDIA RTX Video Super Resolution (VSR) — the sharpest upscaling path for web video and old tapes — requires an RTX 2000-series or newer NVIDIA card. Run aivideoenhancer status to see what your machine supports before starting a batch.

Frequently Asked Questions

Does the CLI cost extra?

No. The CLI, the MCP server, and the Claude Code skill ship in the same installer as the desktop app and are covered by the same $129 one-time license.

Does it work during the free trial?

Yes. The free trial covers the CLI and MCP server too. The first 5 files enhance clean; after that, output carries a small watermark until you register.

Why is there no --json flag?

Human scripts typically parse log output or rely on exit codes. For structured, machine-readable interaction — especially from AI agents — use the MCP server instead. It returns typed tool results designed for assistants.

Same engine, three interfaces

Whether you prefer the wizard, a PowerShell script, or a Claude agent, AI Video Enhancer Studio runs the same local GPU pipeline. Grab the installer, try a batch from the CLI, or wire up MCP and let an agent handle the rest.