lc-editor
lc-editor
一款通过 MCP 客户端驱动的本地视频编辑器。没有可点击的时间轴界面。你发送工具调用;ffmpeg 负责渲染文件。
专为竖屏 9:16 短视频而构建。不含音乐。字幕是带描边和阴影的文字,绝不是文本框。引擎规则写在 specs/craft.md 中。卡拉奇剧集结构是可选预设,而非默认设置。
环境要求
Python 3.11 或更高版本
PATH 中需包含 ffmpeg 和 ffprobe
Related MCP server: melt-7 MCP Server
安装
从本仓库的克隆副本安装:
pipx install .pip install . 也可以。pipx 会将应用安装在其独立环境中,并把 lc-editor 添加到你的 PATH。
从 GitHub 安装:
pipx install git+https://github.com/uzairayed/lc-editor.git运行
lc-editor serve --project ./my-reel--web 会在 127.0.0.1:8765 启动一个可显示静帧的页面。该页面只读。
Cursor
将以下内容添加到你的 MCP 配置中。请使用绝对项目路径。
{
"mcpServers": {
"lc-editor": {
"command": "lc-editor",
"args": ["serve", "--project", "/absolute/path/to/project"]
}
}
}在 Windows 上,路径形如 C:/Users/you/my-reel。
工具
每次编辑都会返回 { ok, timeline_summary, warnings }。非法请求会直接报错。相同的 op_id 重复提交不会产生重复操作。review_report 必须通过后才能执行 export。预览静帧和联系表是磁盘上的 JPEG 文件,而非 base64 数据。
可选:project_create(..., preset="karachi") 会加载系列品牌配置。穆里剪辑不需要此预设。
意外遭遇穆里
将 LC_EDITOR_MURREE_DIR 指向本机上恰好包含 117 张静帧的文件夹,然后:
$env:LC_EDITOR_MURREE_DIR="C:\path\to\murree"
pytest -m murree -sUnix:
LC_EDITOR_MURREE_DIR=/path/to/murree pytest -m murree -s这些静帧保留在本地。它们不在此仓库中。
本版本不包含的功能
多机位、语音转字幕、版权音乐库、节拍同步、Drive 导入,以及可在其中编辑的浏览器界面。
This server cannot be deployed
Maintenance
Related MCP Connectors
Build, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.
Trim, watermark, extract audio, and convert video to 9:16 vertical via API or MCP server.
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
- CueFrameOAuthai.cueframe
Compose, edit and render video with your AI agent. Turn footage into finished edits with content-aware reframing, word-timed captions and motion graphics. Hosted MCP with OAuth sign-in; cloud processing uses credits.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceCreates short videos for TikTok, Instagram Reels, and YouTube Shorts using the Model Context Protocol (MCP) and a REST API.28 npm1,386MIT
- FlicenseNot gradedqualityDmaintenanceEnables agentic video editing and composition via MCP, allowing creation and manipulation of multi-track timelines with clips, transitions, filters, and text overlays, then rendering to MP4 using the melt-7 CLI.-
- AlicenseNot gradedqualityCmaintenanceEnables local-first Instagram reel production entirely over MCP, turning raw footage, URLs, or topics into finished reels with script generation, stock media, voiceover, and captions.2MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to programmatically edit video projects on a local desktop editor, with 119 tools for multitrack editing, effects, captions, audio, and batch auto-editing, producing reviewable and reversible real timeline edits.AGPL 3.0