mcpCut
A real video editor for AI agents, served over MCP, enabling journaled timeline editing, rendering via FFmpeg/MLT, and deterministic CLI operation.
README
mcpCut
A real video editor for AI agents, served over MCP.
mcpCut 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 immutable snapshots with a journaled history of named operations; rendering goes through FFmpeg or the MLT framework; a deterministic CLI twin drives the same logic without a server.
Two ways to use it
☁️ Hosted (fastest — no install). mcpcut.com runs this editor as a service, with a browser editor on top: sign up, create an API token, and point your agent at the cloud MCP endpoint:
claude mcp add --transport http mcpcut https://mcpcut.com/mcp \
--header "Authorization: Bearer <your token>"
You and your agent then work on the same projects — the agent edits over MCP, you review and tweak in the browser editor.
🖥 Self-hosted (this repository). The open, single-user core: run it on your own machine, point your agent at it, keep everything local. No accounts, no browser editor — just the MCP server, the editing engine and the CLI. The rest of this README is about this option.
What the agent gets
44 tools over one consistent model:
- Projects & history — create/list projects, journaled operations
(
editor_get_historyshows 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 rasterized server-side, image/video overlays, covers.
- Audio — music beds, per-clip audio, volume envelopes.
- Media in — local paths or URLs (URL import goes through an SSRF egress guard; media is sanity-checked with ffprobe before it touches a timeline).
- Understanding — media analysis (scenes, audio peaks, keyframes),
auto-captions via faster-whisper (
.[asr]extra), local voiceover via piper (.[tts]extra, GPL — see THIRD_PARTY_NOTICES.md). - Out — validation, preview renders, full exports with presets. Each
export writes an
.mltsidecar you can open in Shotcut or Kdenlive.
Every mutation validates its arguments against the tool's real signature (strings can't leak into numeric filter fields), returns a fresh snapshot with a bumped version, and lands in the journal. Nothing edits in place.
Prerequisites
- Python 3.12+
- FFmpeg (
ffmpeg+ffprobeon PATH) - MLT (
melton PATH) — the default render engine. Alternatively setRENDER_ENGINE=ffmpegand skip melt. - A font for text rendering, e.g. Debian/Ubuntu:
apt install fonts-dejavu-core fonts-noto-color-emoji(elsewhere, pointFONT_PATHat any.ttf).
# Debian/Ubuntu, everything at once:
apt install ffmpeg melt fonts-dejavu-core fonts-noto-color-emoji
Quickstart
git clone https://github.com/musyta-labs/mcpCut && cd mcpCut
python3 -m venv .venv && .venv/bin/pip install -e .
cp .env.example .env # MCP_AUTH_ENABLED=false is already set there
.venv/bin/python -m app.mcp.server
The server starts on http://127.0.0.1:8100 — the MCP endpoint is
http://127.0.0.1:8100/mcp. The database (SQLite) and media workspace are
created on first run.
Or with Docker (ffmpeg, melt and fonts included in the image):
docker build -t mcpcut .
docker run -p 127.0.0.1:8100:8100 -e MCP_TRANSPORT=streamable-http \
-v mcpcut-data:/data mcpcut
Single-user by design. This build has no accounts: whoever can reach the port is the operator, with full tool access including local file paths. Keep it bound to localhost, or put an authenticating reverse proxy in front.
MCP_AUTH_ENABLED=falsemust be set explicitly — the server refuses to start otherwise, so an open port is always a decision you made.
Connect an agent
Claude Code:
claude mcp add --transport http mcpcut http://127.0.0.1:8100/mcp
Any other MCP client, in its JSON config:
{
"mcpServers": {
"mcpcut": { "type": "http", "url": "http://127.0.0.1:8100/mcp" }
}
}
Then ask the agent for something real: “make a 30-second cut of
~/videos/talk.mp4 with auto-captions and export it.” The skills/ directory
contains ready-made instructions you can hand to any agent — see
skills/README.md.
Or drive it without a server
The CLI twin runs the same operations deterministically:
echo '{"op": "create_project", "args": {"metadata": {}}}' > /tmp/ops.json
.venv/bin/python -m app.mcp.cli /tmp/ops.json
Configuration
Everything lives in environment variables (or .env); see
.env.example for the full annotated list. The ones that
matter most:
| Variable | Default | What it does |
|---|---|---|
MCP_AUTH_ENABLED |
true |
must be set to false in this build (see above) |
DATABASE_URL |
sqlite:///./data/editor.db |
SQLite by default; Postgres via .[postgres] |
MEDIA_DIR |
./media |
originals, exports, previews, caches |
MCP_HOST / MCP_PORT |
0.0.0.0 / 8100 |
bind address of the server |
RENDER_ENGINE |
mlt |
mlt or ffmpeg |
FONT_PATH |
DejaVu Bold (Debian path) | font for text overlays and captions |
EXPORT_TTL_HOURS / CLIP_CACHE_TTL_HOURS |
24 / 48 |
retention sweep; RETENTION_ENABLED=false disables it |
Retention is real: a background daemon deletes exports after 24 h and
cached clips after 48 h by default. On a personal machine either download
your exports promptly or set RETENTION_ENABLED=false.
How it's built
| Layer | Where | What |
|---|---|---|
| Timeline model | app/editor/model.py |
frozen dataclasses; every edit returns a new project, version + 1 |
| Mutations | app/editor/mutations.py |
pure functions, one named journaled operation per gesture |
| Validation | app/editor/validation.py |
structural checks + opt-in shorts profile |
| Render | app/editor/render.py |
one contract, two engines: mlt_graph.py (default) and ffmpeg_graph.py |
| Analysis | app/analysis/ |
scenes, peaks, keyframes — feeds the agent's decisions |
| Storage | app/db/ |
SQLite/Postgres via SQLAlchemy + Alembic; append-only operation journal |
| MCP server | app/mcp/server.py |
streamable-http or stdio; tool schemas derived from real signatures |
| CLI twin | app/mcp/cli.py |
same operations, no server, deterministic |
Safety properties the codebase holds everywhere: no shell=True (argv lists
only), timeouts on every subprocess, atomic export writes, SSRF egress guard
on URL imports, argument validation derived from tool signatures.
License
MIT. Third-party obligations (FFmpeg/MLT installed by you, the
GPL piper-tts extra, fonts) are documented in
THIRD_PARTY_NOTICES.md.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。