ShortsFlow
Related Servers
Alternatives to ShortsFlow
- AlicenseNot gradedqualityBmaintenanceAI-native timeline editor for short-form video. Your agent cuts, captions, adds motion graphics and renders against a real, editable timeline over MCP — not a render queue. Human-in-the-loop by design: it calls request_review and waits while you supervise in a browser. Local-first and AGPL; your footage never leaves your machine.2AGPL 3.0
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that gives agents a video engine for cutting beat-synced 9:16 shorts from existing footage, generating original short films from a prompt, and swapping characters in a clip while preserving motion and sound. It handles the deterministic work — scene detection, tracked crops, captions and rendering — while generation runs on private Hugging Face ZeroGPU Spaces in the user's own account.Apache 2.0
- FlicenseNot gradedqualityAmaintenanceA local MCP server that lets chat-based coding agents turn a folder of raw clips into finished, beat-synced montage videos by handling shot selection, music matching, subtitles, transitions, and rendering through natural language. It returns a timeline digest and contact sheet for approval before any frame is rendered.-
- AlicenseNot gradedqualityDmaintenanceAutomated short-form video creation from text prompts, combining text-to-speech, captions, background videos, and music, exposed as an MCP server for AI agents.76 npmMIT
- AlicenseAqualityCmaintenanceEnables MCP clients to transcribe audio/video files locally, generate SRT subtitles, and burn captions into videos via tool calls, without a cloud API.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables any MCP-capable IDE agent to research topics, write scripts, synthesize narration, generate scene imagery, and render 1080p landscape masters plus vertical Shorts through FFmpeg with broadcast-grade audio and hard quality gates. Exposes 13 tools over a Cloudflare Remote MCP endpoint that cuts prompt token usage by roughly 80% compared with local stdio.6 npmMIT
- FlicenseNot gradedqualityAmaintenanceA local MCP server that lets AI coding agents turn a folder of raw video clips into a finished montage from a single natural-language prompt, handling clip analysis, shot selection, beat-synced cuts, music matching, subtitles, transitions, and picture-in-picture. Each turn returns a reviewable timeline digest and contact sheet so nothing is rendered until the user approves the plan.-
TDQS
Scored across 5 tools
Each tool has a clearly distinct role: creating a short from a topic (generate_short), clipping an existing video (extract_clips), polling jobs (get_render_status), enumerating options (list_supported_modes) and writing social copy (generate_social_package). The descriptions explicitly contrast the two easily-confused generation paths ("use extract_clips instead"), eliminating the main ambiguity risk.
All names are snake_case and verb-first (generate_*, get_*, list_*, extract_*), following a single predictable verb_noun convention. No mixing of styles or vague bare nouns.
Five tools is tightly scoped to the server's purpose: two job-starting tools, one poller, one options lookup and one text generator. Nothing is redundant and no trivial tool is padded in.
The core lifecycle (start job → poll status → get options → produce metadata) is fully covered, and the async pattern is documented in each tool. Minor gaps remain: no job cancel/list, and get_render_status does not advertise returning the output file path, which agents would likely need to locate the finished video.