melt-7 MCP Server
Provides tools to probe media files using ffprobe, enabling retrieval of metadata such as duration, resolution, fps, and codecs.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
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.txtRelated MCP server: mcpCut
Running
python mcp_server.pyServes 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).
Running as a service
A systemd user unit is provided for running the server persistently:
python3 -m venv .venv
.venv/bin/pip install -r requirements.txt
cp melt-7-mcp.service ~/.config/systemd/user/
systemctl --user daemon-reload
systemctl --user enable --now melt-7-mcp.serviceCheck status/logs with systemctl --user status melt-7-mcp.service and
journalctl --user -u melt-7-mcp.service -f.
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 |
| Start a new project at a given MLT profile (resolution/fps) |
| List all projects with track/clip counts |
| Raw MLT XML + human-readable summary |
| Delete a project and its renders |
| ffprobe a media file (duration, resolution, fps, codecs) |
| Add a track to the timeline |
| Remove a track |
| Place a clip (file path or |
| Change a clip's in/out points |
| Move a clip (leaves a blank gap behind) |
| Remove a clip (leaves a blank gap) |
| Composite/wipe/mix between two tracks |
| Attach a filter to a track, clip, or the whole project |
| Remove a filter |
| Convenience wrapper for a |
| Discover available producers/filters/transitions/consumers/profiles |
| Escape hatch for anything the above don't cover |
| 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.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
AI video editor for agents and humans: timeline, captions, color, audio and generation as MCP tools.
AI video editor your agent can drive: plan scenes, edit a multi-track timeline, and render MP4s.
Autonomous AI video editor over MCP: viral clips, captions, reframe, chroma key, MP4 export.
Autonomous AI video editor over MCP: 37 tools, 189+ actions, 280+ caption templates, MP4 export.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to perform deterministic video editing operations like trim, resize, add text, and more using MCP tools.5 npm5MIT
- AlicenseNot gradedqualityCmaintenanceA real video editor for AI agents, served over MCP, enabling journaled timeline editing, rendering via FFmpeg/MLT, and deterministic CLI operation.1MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that gives AI agents a stateful multi-track video editor powered by MLT, enabling them to assemble timelines, add media and text, apply filters and transforms, preview downscaled frames, and render final videos to disk.MIT
- AlicenseNot gradedqualityCmaintenanceEnables automated, transactional video editing for Kdenlive, providing tools for timeline manipulation, effects, graphics, captions, visualization, and project export through a local MCP server and scriptable CLI.MIT