Mcpcut

io.github.musyta-labsPublished by GitHub account musyta-labsv0.1.1Updated Oct 25, 2026

Orccut: a real timeline video editor for AI agents - journaled edits, FFmpeg/MLT rendering

VerifiedStreamable HTTPWeb executableProductivity & WorkflowMedia & Design

Overview

AI-generated overview

Orccut is a remote MCP video editor that lets an AI assistant build and export timeline-based video projects with journaled, versioned edits.

What you can do
Create and list projects, review journaled edit history, manage named versions with restore, and add annotations. Build multi-track timelines with clips, trims, splits, moves, keyframes, transitions, canvas fit and color adjustments. Add text overlays, image and video overlays, covers, music beds, per-clip audio and volume envelopes. Import media by http(s) URL with server-side download and checks, and analyze scenes, audio peaks and keyframes. Generate auto-captions and voiceover, then validate, preview frames and export with presets.
When to use it
Useful when you want an assistant to assemble or revise a real video edit — cuts, titles, captions, audio and exports — on projects you can also open and adjust in a browser editor. Suited to agent-driven editing workflows rather than one-off ffmpeg commands.
Requirements
A remote MCP endpoint at orccut.com over streamable HTTP, with OAuth authentication. An Orccut account and an API token sent as an Authorization Bearer header. Network access to the endpoint and to any media URLs you import.
Before you install
Requires an account and an API token; keep the token secret. The agent can create, modify and export projects and download media from URLs you supply, so review edits before relying on them. Media is fetched server-side by Orccut, so imported URLs are shared with that service.

Installation

In SourceWeft

  1. Open Mcpcut in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.musyta-labs%2Fmcpcut/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "mcpcut": {
      "type": "http",
      "url": "https://orccut.com/mcp"
    }
  }
}

README

Orccut

A real video editor for AI agents, served over MCP.

Orccut gives any MCP-capable agent (Claude Code, Claude Desktop, or anything else that speaks the protocol) an actual editing model — not a wrapper around one ffmpeg command. Projects are timeline snapshots with a journaled history of named operations; you and your agent work on the same projects — the agent edits over MCP, you review and tweak in the browser editor at orccut.com.

Connect your agent

  1. Sign up at orccut.com and create an API token.
  2. Point your agent at the MCP endpoint.

Claude Code:

bash
claude mcp add --transport http orccut https://orccut.com/mcp \  --header "Authorization: Bearer <your token>"

Any other MCP client, in its JSON config:

json
{  "mcpServers": {    "orccut": {      "type": "http",      "url": "https://orccut.com/mcp",      "headers": { "Authorization": "Bearer <your token>" }    }  }}

Then ask the agent for something real: “make a 30-second cut of this video with a title and captions, and export it.”

What the agent gets

44 tools over one consistent model:

  • Projects & history — create/list projects, journaled operations (editor_get_history shows every edit ever made), named versions with restore, annotations.
  • Timeline — multiple video/audio tracks, clips with trim/split/move/ resize, transforms with keyframes, transitions, canvas fit, color adjustments.
  • Text & graphics — text overlays, image/video overlays, covers.
  • Audio — music beds, per-clip audio, volume envelopes.
  • Media in — media by http(s) URL, downloaded and checked server-side before it touches a timeline.
  • Understanding — media analysis (scenes, audio peaks, keyframes), auto-captions, voiceover.
  • Out — validation, preview frames, full exports with presets.

Every edit validates its arguments, returns a fresh project snapshot with a bumped version, and lands in the journal. Nothing edits in place.

Tool documentation

The skills/ directory documents the tool surface as ready-made instructions you can hand to any agent: video-editing walks through the full workflow — project → media → timeline edits → captions → validate → export — and the conventions that make agent edits reliable.

License

The documentation in this repository is released under the MIT license.

Source: README.md at commit 9e07cbb

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

2
  1. v0.1.1LatestSep 30, 2026
  2. v0.1.0Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts