Kinocut runs on your own machine — the client starts it, so there is no endpoint to ping. 2 586 installs a week from pypi. Last commit 16 Sep 2026.
Guardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
frame_path = os.path.join(tmp_dir, f"candidate_{i:03d}.jpg")
result = subprocess.run(demucs_cmd, capture_output=True, text=True, timeout=DEFAULT_AI_TIMEOUT) # noqa: S603
const child = spawn(runtime.python, ["-I", "-s", "-m", "kinocut", "--mcp"], {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add kinocut -- uvx kinocut
{
"mcpServers": {
"kinocut": {
"args": [
"kinocut"
],
"command": "uvx"
}
}
}
[mcp_servers.kinocut]
command = "uvx"
args = ["kinocut"]
{
"mcpServers": {
"kinocut": {
"args": [
"kinocut"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"kinocut": {
"args": [
"kinocut"
],
"command": "uvx"
}
}
}
AI video editor: create projects, edit timelines, add captions and effects, and render videos.
Edit video by talking to your AI — search footage, cut timelines, apply effects, add captions.
FFmpeg as a service for AI agents: typed video editing tools, async jobs, downloadable outputs.
Independent effect verification and signed receipts for consequential AI agent actions.
Constitutional guardrails and loop detection for AI agents
Transform video, audio and images, and generate media from prompts. FFmpeg, captions, models.
Edit uploaded footage with AI tools: cuts, captions, reframing and previews. Final export in Studio.
Make videos AI-readable. Extract timestamped frames and transcripts from any video for AI agents.
Answers built from our own checks of this server.