FilmCraft MCP (agent-driven video editor) — workflow skill for AI editing agents

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page. From a terminal: curl -fsSL https://varg.ai/install | sh installs the vargai CLI (https://varg.ai/how-to/cli.md): vargai search and vargai install <slug> with no key, every varg model after vargai login.

Open-source Rust non-linear editor with 650+ commands exposed over MCP and CLI, so an agent can cut, trim, grade, mix and export like an editor.

What it does

Professional NLE (three-point editing, ripple/roll/slip/slide, color wheels, curves, HSL secondary, 90+ effects, EBU R128 loudness) with its own codecs (no ffmpeg). The UI, CLI, JSON control channel and MCP server dispatch the same commands; the README trailer and grades were built by an agent driving the app. Sibling EffectCraft (motion graphics/compositing, 308 effects, Lottie import/export) exposes the same MCP surface.

Use when

Not for

Install

Example output

https://raw.githubusercontent.com/storytold/filmcraft/main/docs/images/filmcraft-hero.png — FilmCraft's timeline editor (README hero) (credit: ArtCraft (storytold) (README), https://github.com/storytold/filmcraft)

More AI editing agents skills