melt-7 MCP Server
Enables 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.
README
melt-7 MCP Server
An MCP server exposing melt-7 (the MLT Multimedia Framework's CLI rendering engine -- the same backend Kdenlive uses) for agentic video editing/composition: build a multi-track timeline with clips, transitions, filters, and text overlays, then render it to MP4.
Requirements
melt-7andffprobe/ffmpegonPATH(Fedora:dnf install mlt)- Python 3.10+
pip install -r requirements.txt
Running
python mcp_server.py
Serves MCP over streamable HTTP on http://0.0.0.0:8001/mcp (port 8001, to
avoid colliding with the wan2_2_t2v server on 8000 if both run on the same host).
Project model
Each call to create_project creates a project directory under projects/<id>/
holding project.mlt (the authoritative MLT XML, hand-rolled to a flat schema
rather than Kdenlive's nested per-track-tractor convention), meta.json (display
name/profile bookkeeping), and a renders/ directory for rendered output. Every
tool re-reads project.mlt fresh and atomically rewrites it, so state survives
server restarts -- there is no in-memory project cache.
Tools
| Tool | Purpose |
|---|---|
create_project(name, profile) |
Start a new project at a given MLT profile (resolution/fps) |
list_projects() |
List all projects with track/clip counts |
get_project_xml(project_id) |
Raw MLT XML + human-readable summary |
delete_project(project_id) |
Delete a project and its renders |
probe_clip(file_path) |
ffprobe a media file (duration, resolution, fps, codecs) |
add_track(project_id, kind, position) |
Add a track to the timeline |
remove_track(project_id, track_id) |
Remove a track |
add_clip(project_id, track_id, source, clip_in, clip_out, position) |
Place a clip (file path or color:/noise: generator) |
trim_clip(project_id, track_id, clip_index, clip_in, clip_out) |
Change a clip's in/out points |
move_clip(project_id, track_id, clip_index, new_position, new_track_id) |
Move a clip (leaves a blank gap behind) |
remove_clip(project_id, track_id, clip_index) |
Remove a clip (leaves a blank gap) |
add_transition(project_id, track_a, track_b, service, properties) |
Composite/wipe/mix between two tracks |
add_filter(project_id, target, service, properties, clip_index) |
Attach a filter to a track, clip, or the whole project |
remove_filter(project_id, filter_id) |
Remove a filter |
add_text_overlay(project_id, track_id, text, ...) |
Convenience wrapper for a qtext title clip |
query_services(kind, service_id) |
Discover available producers/filters/transitions/consumers/profiles |
set_raw_xml_property / remove_raw_xml_property / inject_raw_xml |
Escape hatch for anything the above don't cover |
render_project(project_id, output_name, vcodec, acodec, extra_args, timeout_seconds) |
Render the timeline to MP4 (synchronous) |
Notes on reliability
melt-7's process exit code is not a reliable success signal -- it can
exit 0 while logging a "failed to load producer" error and silently
substituting a blank clip. render_project verifies success independently:
the output file must exist, be ffprobe-readable, have a duration close to
the project's expected duration, and stdout/stderr must contain no known
failure markers.
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。