StudioMeyer Video

io.studiomeyer由 studiomeyer.io 發布v1.0.4更新於 Nov 3, 2026

影片製作:錄製、剪輯、特效、字幕、TTS、截圖。8 個工具。

AI 翻譯由 AI 模型根據下方的原文描述翻譯,可能有誤。

原文描述

Video production: recording, editing, effects, captions, TTS, screenshots. 8 tools.

發布方自己的服務:StudioMeyer Crew

已驗證STDIO僅桌面瀏覽器自動化媒體與設計

概覽

StudioMeyer Video 的本機 MCP 服務,由 studiomeyer.io 發布;無需登入;STDIO;8 個工具。

暫無 AI 概覽:以下資訊來自註冊中心條目和服務本身。

發布者
studiomeyer.io

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 StudioMeyer Video,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Part of the StudioMeyer MCP Stack — Built in Mallorca 🌴 · ⭐ if you use it

mcp-video

[npm version] [npm downloads] [License] [Last commit] [GitHub stars]

**Cinema-grade video production for AI agents.**

[CI] [License: MIT] [TypeScript] [Version] [npm version] [Node]

8 MCP tools for recording, editing, effects, captions, TTS, and smart screenshots.
Built on ffmpeg and Playwright. Works with any MCP client.

Features · Quick Start · Examples · Architecture

A note from us

We have been building tools and systems for ourselves for the past two years. The fact that this repo is small and has few stars is not because it is new. It is because we only just decided to share what we have built. It is not a fresh experiment, it is a long story with a recent commit.

We love building things and sharing them. We do not love social media tactics, growth hacks, or chasing stars and followers. So this repo is small. The code is real, it gets used, issues get answered. Judge for yourself.

If it helps you, sharing, testing, and feedback help us. If it could be better, an issue is more useful. If you build something with it, tell us at [email protected]. That genuinely makes our day.

From a small studio in Palma de Mallorca.

Features

ToolOperationsDescription
video_recordcinema, scroll, multi-deviceRecord websites at 60fps with frame-by-frame capture
video_editspeed, crop, reverse, keyframe, pipEdit clips with zoom/pan, PiP, slow-mo
video_colorgrade, effect, lut, chromaColor grading, 22 LUT presets, green screen
video_audioextract, music, ducking, mix, voiceAudio extraction, mixing, 9 voice effects
video_textsubtitles, caption, overlay, animateBurn SRT, Whisper auto-caption, 15 text animations
video_composeconcat, intro, social, beat-sync, templatesJoin clips, social format conversion, beat sync
video_speechgenerate, voices, narratedElevenLabs/OpenAI TTS, full narrated videos
video_screenshotcapture, detectElement-aware screenshots, page feature detection

Highlights

  • 60fps frame-by-frame capture — Playwright screenshots every frame, ffmpeg encodes. Zero frame drops.
  • Cinema easing curves — 16 easing options including cinematic and showcase for buttery smooth scrolling.
  • Smart screenshots — Auto-detects 15+ UI elements (chat widgets, pricing sections, booking forms, etc.).
  • Narrated videos — Provide a URL + script, get a professional video with synchronized AI voiceover.
  • 22 LUT presets — Film-grade color grading (teal-orange, noir, vintage, cyberpunk, etc.).
  • Social format export — One-click conversion to Instagram Reel, TikTok, YouTube Short, LinkedIn.
  • Dual transport — Stdio (default) or HTTP mode for persistent microservice deployment.

Prerequisites

  • Node.js >= 18
  • ffmpeg and ffprobe (validated on startup, cross-platform)
  • Playwright browsers (npx playwright install chromium)
  • Optional: ELEVENLABS_API_KEY for ElevenLabs TTS
  • Optional: OPENAI_API_KEY for Whisper captions and OpenAI TTS

If ffmpeg lives outside PATH, set FFMPEG_PATH and FFPROBE_PATH to the absolute binary paths. Both env vars are honoured at startup AND at every runtime spawn site.

Quick Start

With Claude Code (stdio)

json
{  "mcpServers": {    "video": {      "command": "npx",      "args": ["-y", "@studiomeyer/mcp-video"]    }  }}

With npx

bash
npx @studiomeyer/mcp-video

From source

bash
git clone https://github.com/studiomeyer-io/mcp-video.gitcd mcp-videonpm installnpx playwright install chromiumnpm run buildnpm start

HTTP mode

bash
# Start as HTTP microservicenpx @studiomeyer/mcp-video --http --port=9847
# Or via environment variablesMCP_HTTP=1 MCP_PORT=9847 npx @studiomeyer/mcp-video

Configuration

Environment VariableDefaultDescription
VIDEO_OUTPUT_DIR./outputDirectory for generated files
FFMPEG_PATH—Absolute path to ffmpeg binary if not on PATH
FFPROBE_PATH—Absolute path to ffprobe binary if not on PATH
ELEVENLABS_API_KEY—ElevenLabs TTS API key
OPENAI_API_KEY—OpenAI API key (Whisper + TTS)
MCP_HTTPfalseEnable HTTP transport
MCP_PORT9847HTTP port
MCP_HOST127.0.0.1HTTP bind address
MCP_VIDEO_DEBUGfalseEnable debug logging
MCP_VIDEO_ALLOW_INTERNALfalseSet to 1 to allow URLs that resolve to localhost / private / metadata IPs. Local dev only — leave unset in production (SSRF guard).

What You Can Build

Use CaseTools UsedOutput
Product demo videovideo_record → video_text → video_audio60fps website recording + auto-captions + background music
Social media clipsvideo_record → video_composeRecord once → export to Instagram Reel, TikTok, YouTube Short
Narrated explainervideo_speech → video_colorAI voiceover + cinematic color grade
Before/after comparisonvideo_screenshot → video_editSmart element screenshots + PiP composition
Automated QAvideo_record + video_screenshotRecord user flows + screenshot specific elements

Usage Examples

Record a website

Use video_record with type "cinema" to record https://example.comwith a smooth scroll and hover over the navbar.

Create a narrated explainer video

Use video_speech with type "narrated" to create a narrated video ofhttps://example.com with these segments:1. "Welcome to our homepage" — pause on hero section2. "Check out our features" — scroll to features3. "Get started today" — hover over CTA button

Auto-caption a video

Use video_text with type "caption" to add auto-generated captionsto /path/to/video.mp4

Export for social media

Use video_compose with type "social-all" to convert/path/to/video.mp4 to all social media formats.

Smart screenshot

Use video_screenshot with type "capture" to screenshot the chat widgetand pricing section on https://example.com

Architecture

src/  server.ts            Entry point, 8 consolidated MCP tools  lib/                 Logger, types, dual transport  handlers/            Tool handlers (video, editing, post-production, tts, screenshots)  schemas/             JSON Schema definitions for legacy tool format  tools/    engine/            Core engines      capture.ts       Frame-by-frame recording (Playwright → PNG → ffmpeg)      encoder.ts       ffmpeg encoding pipeline      scenes.ts        Scene execution (scroll, hover, click, type, wait)      cursor.ts        Visible cursor simulation      smart-screenshot.ts  Element-aware screenshot engine      tts.ts           ElevenLabs + OpenAI TTS with fallback      narrated-video.ts    Full narration pipeline      social-format.ts     Social media format conversion      concat.ts        Video concatenation with transitions      lut-presets.ts   22 cinema LUT presets      ...and more

Development

bash
npm run dev          # Start with tsx (hot reload)npm run typecheck    # Type checknpm test             # Run testsnpm run check        # Verify ffmpeg/ffprobe installed

About StudioMeyer

StudioMeyer is an AI and design studio based in Palma de Mallorca, working with clients worldwide. We build custom websites and AI infrastructure for small and medium businesses. Production stack on Claude Agent SDK, MCP and n8n, with Sentry, Langfuse and LangGraph for observability and an in-house guard layer.

License

MIT

Credits

Built by StudioMeyer. Part of our open-source toolkit for AI-powered content creation.

來源:README.md,提交 8354b40

工具

8

video_record

Record Website Video

Record website videos. Types: cinema (full 60fps with scenes/cursor), scroll (quick scroll-through), multi-device (desktop+tablet+mobile).

輸入參數url必填type必填

video_edit

Edit Video

Edit video clips. Types: speed (0.25x-4x), crop (region), reverse (± audio), keyframe (zoom/pan animation), pip (picture-in-picture overlay).

輸入參數type必填

video_color

Color & Effects

Color grading & visual effects. Types: grade (brightness/contrast/saturation/gamma/temperature), effect (blur/sharpen/vignette/grayscale/sepia/noise/glow), lut (22 cinema presets), chroma (green/blue screen replacement).

輸入參數type必填

video_audio

Audio Tools

Audio operations. Types: extract (MP3/AAC/WAV/FLAC from video), music (add background music with fade), ducking (auto volume reduction), mix (multi-track mixing), voice (9 voice effects: echo/reverb/deep/chipmunk/robot/whisper/radio/megaphone/underwater).

輸入參數type必填

video_text

Text & Captions

Text overlays & captions. Types: subtitles (burn SRT/ASS), caption (Whisper AI auto-caption), overlay (animated text layers), animate (15 text animation styles).

輸入參數type必填

video_compose

Compose & Export

Compose and export videos. Types: concat (join clips with transitions), intro (animated intro/outro), social (convert to Instagram/TikTok/YouTube/LinkedIn), social-all (batch all platforms), beat-sync (cut on music beats), templates (list available), render (render from template).

輸入參數type必填

video_speech

Speech & Narration

Text-to-speech & narrated videos. Types: generate (ElevenLabs/OpenAI TTS), voices (list available voices), narrated (full narrated video: script → TTS → website recording → sync → MP4).

輸入參數type必填

video_screenshot

Smart Screenshot

Smart element-aware screenshots. Types: capture (detect & screenshot specific page features: chat, pricing, hero, etc.), detect (analyze page features without screenshotting).

輸入參數url必填type必填

版本歷史

2
  1. v1.0.4最新Nov 3, 2026
  2. v1.0.3Sep 16, 2026

評分

已滿足適用檢查項的 90%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分
  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Studiomeyer 整合