MCP servers and skills: search, filter by where they run, and compare.
1–24 of 77 tools for “scene-detection”
Clear allClaude Code / Codex skills that turn a video into a Chinese narration recap (视频解说): scene detection, ASR, VLM, script, TTS, ffmpeg assembly, optional editable JianYing / CapCut draft export (剪映草稿导出).
SkillMIT★ 590No key
Prompt-driven AI video editor for Shorts and long-form. (0.0.0 <= v < 0.5.0: [Pre-Alpha])
Node.jsMIT★ 88No key
A Cursor Skill for deep analysis of YouTube videos using scene detection, subtitle alignment, and parallel frame analysis.
SkillMIT★ 1Few starsNo key
AE-for-AI: Claude watches videos and replicates them as Remotion code. MCP + web UI + motion profile pipeline.
PythonMIT★ 2Few starsNo key
Debug UI bugs from screencasts: an Agent Skill that extracts key frames via ffmpeg scene detection so coding agents can visually inspect what went wrong.
SkillMIT★ 5No key
Professional video editing skill for Hermes Agent — AI captioning, silence removal, scene detection, stabilisation, smart reframing, and more. All free and open source.
SkillMIT★ 7No key
Video analysis MCP plugin for Claude Code — scene detection, local transcription, keyframe extraction. All local, zero cost, full privacy.
Node.jsMIT★ 7No key
Local-first MCP server for video: download any video from almost any URL, or get a transcript plus scene-aware deduplicated keyframes. YouTube, TikTok, Instagram, X, WeChat Channels, MP4/HLS. No cloud
Node.jsMIT★ 7No key
YOLO real-time object detection dashboard with MCP integration
SkillMIT★ 2Few starsNo key
Video analysis plugin for Claude Code. Feed it a bug report recording, get back steps-to-reproduce, error messages, and timestamps.
SkillMIT★ 1Few starsNo key
costrict-plugins mirror of github-trending-heimdall (auto-generated, do not edit)
SkillMITFew starsNo key
AI Film Studio — end-to-end agent skill for short films. Nano Banana 2 + Veo 3.1 + Seedance 2.0 + LTX 2.3 + ElevenLabs + Remotion.
SkillMIT★ 9No key
Turn any video into LLM-ready data - transcripts, speaker labels, scenes, subtitles and on-screen text. Self-hostable, keyless, MCP-ready.
Node.jsAGPL-3.0★ 3Few starsNo key
Give any AI the ability to watch YouTube videos. Dense frame↔transcript interleaving. Gemini-style video understanding for any model. MCP server.
SkillMIT★ 5No key
An MCP server that gives AI agents local video tools: metadata, shot detection, frame extraction, and keyframe checks. Runs FFmpeg on your machine. No API key.
Node.jsMIT★ 1Few starsNo key
vision-foundation-mcp 是一个基于MCP（Model Context Protocol）的视觉理解服务，通过stdio协议向Claude等AI助手提供本地图像分析能力。 核心价值：允许AI助手在本地运行视觉模型分析图像，无需将图片上传到云端，保护用户隐私并降低成本。
Node.jsMIT★ 1Few starsNo key
Turn a lecture video into AI-readable context: one markdown section per screen, with the frames and the transcript that belong to it. Agent-first CLI.
SkillMIT★ 3Few starsNo key
Screen recording CLI + MCP server for AI agents. Zero cost. 100% local.
Node.jsApache-2.0★ 1Few starsNo key
🎬 一键自动剪辑高燃视频片段配卡点BGM — 5种音乐风格/4种混音预设/Tunee AI专业BGM/双源配乐
SkillMIT★ 4Few starsNo key
Local-first Codex plugin that indexes long videos with OCR/ASR and answers with timestamped, SHA-verified visual evidence.
SkillApache-2.0★ 4Few starsNo key
Camera vision MCP server: multi-camera, gesture recognition, object detection, scene understanding. Give your AI agent eyes
PythonMIT★ 1Few starsNo key
Claude Code plugin: extract scene-change frames + audio transcript from any video so Claude can 'watch' it.
SkillMIT★ 3Few starsNo key
Who stands behind it
