Self-hosted FFmpeg media processing for AI agents and apps via HTTP and MCP, with optional natural-language workflows and A2A support.

Parallel video rendering with live dashboard, GPU auto-detection, checkpoint system, and stream-copy concat. Includes an MCP server, a Claude Code skill, and a CLI.

Everyday media jobs by intent for AI assistants over MCP: compress to a target size, trim, GIF, extract audio. Dry-run shows the exact ffmpeg command. PyPI: mediakit-mcp.

Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

Parallel video rendering with live dashboard, GPU auto-detection, and stream-copy concat. MCP server with 7 typed tools for AI agents, a Claude Code skill, and a CLI.

A free and open-source multimedia toolkit built on FFmpeg. Convert, compress, extract, cut and batch-process audio, video and images, or drive the same engine from the CLI, an MCP server or the AI Copilot.

Headless, agent-native video editing CLI and MCP server. Cut, trim, caption, analyze and render real timelines from natural language or scripts instead of hand-writing ffmpeg filtergraphs.

A MCP server that adds subtitles to videos using FFmpeg and OpenAI Whisper API.

MCP server for downloading and converting videos with yt-dlp and FFmpeg

Parallel YouTube clipping for AI agents — MCP server + CLI on yt-dlp and ffmpeg

Local desktop studio for Whisper AI speech transcription, subtitle translation, OCR masking, and FFmpeg burning

Video Effects MCP server — FFmpeg video effects via natural language. Color grade, transitions, chroma key, text overlays, blur, speed, crop, concat. 9 operations.

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

MCP speech-to-text server: FastAPI + fastapi-mcp, FFmpeg preprocessing, and policy-based routing across OpenAI and Groq via LiteLLM.

Let AI agents record the Windows screen, watch it as frames, and edit it with ffmpeg

MCP server that lets Claude and other AI assistants see videos with FFmpeg and cut them with LosslessCut

Non-linear video editor an AI agent can actually drive (MCP), with a web UI. Timeline -> ffmpeg.

MCP server for Kdenlive: AI-driven video editing, effects, and color grading with MLT and FFmpeg

Let AI agents record the Windows screen, watch it as frames, and edit it with ffmpeg

MCP server that gives Claude Code the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends

A free package registry for video pipelines: install recipes and WebAssembly filters, written in SQL and compiled to ffmpeg commands you can read.

Universal MCP server that gives AI assistants the ability to watch and understand videos — extracts frames via ffmpeg and processes audio via multiple backends

3D Device Mockup Studio - Create professional app promo videos with 3D effects, annotations, and screen overlays. Built with Tauri + React Three Fiber + FFmpeg.

Cinema-grade video production MCP server — 8 tools for recording, editing, effects, captions, TTS, and smart screenshots. Built on ffmpeg + Playwright.

Video editing and rendering for coding agents. Open-source CLI and MCP server for Claude Code, Codex and Cursor. Runs locally on ffmpeg, free.

Author a video as JSON, render it anywhere. Rust video engine behind PromoShot — CLI + MCP server for AI agents, wgpu + ffmpeg, runs headless on Linux.

Turn audio into vertical short videos with AI images, word-timed captions and FFmpeg: a CLI and MCP server for Reels, TikTok and YouTube Shorts.

Local-first video editor for people and AI agents. Create in the Studio or via MCP, REST API and CLI; render with FFmpeg.

Zero-API Facebook & Instagram Autonomous Studio powered by Playwright Persistent Context, yt-dlp, FFmpeg, 82-Rule Humanizer, Local Ollama, and Claude/Cursor MCP Server

Remote MCP server for KinoPipe: typed video editing (FFmpeg as a service) for AI agents. 39 tools, OAuth 2.1, async jobs, signed outputs.

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.

MCP server for image-and-video-compressor — lets coding agents compress images and videos, probe media, and discover what the local ffmpeg and sharp builds actually support.

Lightweight Quran recitation video maker: background clips, smooth transitions, keyed recitation layer and Arabic title cards — FFmpeg, desktop app, CLI and MCP server. Runs on an 8 GB laptop.

54-tool MCP server for multimodal automation the only open-source MCP with full PPTX/DOCX/PDF lifecycle, plus FFmpeg, GIMP, Inkscape, Blender, FreeCAD, MATLAB, Godot integration. 7 MCP services orchestrated in one workspace.

MCP server with 55 tools for Claude Code, Claude Desktop and Cursor: exact math, dates and public holidays, CSV, SQLite, PDF, files, ports and ffmpeg helpers. Zero dependencies, only Node.js.

?? Topic ? narrated, subtitled short video (YouTube Shorts / TikTok / Reels) inside Claude. MoneyPrinterTurbo-style MCP server + Claude Code plugin: free neural voices, stock footage, word-highlight subtitles, ffmpeg. No LLM API key.

A self-hosted MCP server that can expose local media-generation backends such as ComfyUI and Blender while also providing local media analysis, editing, FFmpeg, HyperFrames, timeline, subtitle, speech, and audio utilities. The project is designed for Portainer-only deployments

Video frame extraction & composition service for AI vision pipelines, extracts frames via FFmpeg and composes them into 1×1/2×2/4×4 grid sheets for multimodal LLMs. REST API, Web UI, and MCP server over one core engine.

Give your AI agent a video ad studio. It decodes a winning ad shot by shot, then edits 9:16 ads from your own footage: captions, voice-over, deterministic ffmpeg render and QC. MCP server for Claude Code, Codex, Cursor.

Meme video clips for AI agents: search (Vlipsy API, BYO key) or local folders, preview, fetch with credits, and drop into ffmpeg renders, Premiere/Resolve/Final Cut timelines (OTIO, FCPXML, XML, EDL), Remotion or HyperFrames. CLI + MCP server, zero deps.

Tell an AI to edit your video and watch it happen. A real non-linear editor with a timeline, plus 83 tools an agent can call over MCP — works with Claude Code, Cursor and Codex. Runs locally on a deterministic ffmpeg engine.

Free, local video editing engine for AI agents: cut, caption, reframe and render short-form video with FFmpeg, analyse a viral video and reuse its format as a template. CLI + MCP server for Claude, Cursor, Codex, Gemini, Grok and Manus. No cloud, no API key.

Open-source AI video editor for Claude Code and any MCP client. Removes silence and repeated takes, edits by transcript with local whisper.cpp, adds captions, and exports to Final Cut Pro, DaVinci Resolve and Premiere Pro. CLI, MCP server and browser timeline over FFmpeg. MIT, local, no API key.

Make my clips look like that video. Zing studies a video you like and cuts your clips into captioned drafts in that style, in 16:9, square and 9:16, and makes memes from local photos. Pre-alpha local CLI and MCP server; installs from source with Python, uv and FFmpeg.

Kine（/kaɪn/）· 为 AI 智能体设计的确定性视频剪辑/合成引擎：第 N 帧 = f(N)。TypeScript monorepo（8 包）+ Edge CDP 逐帧抓帧 + ffmpeg 分片编码 + Python 侧车。能力：32 个 CLI/MCP 工具，读事实→改 DSL→量结果→验证出片；声明式 timeline.yaml 单一真源；逐帧确定性渲染、字节级复现；8 类指标 + 断言集 + 基线回归；34 个 widget；15 种转场；离线 SFX；字幕；浅色模式。已出片 world.execute(me) MV（25 幕 / 121.9s）等。

Let any LLM agent actually watch videos. The watch_video tool takes a URL or local file and returns scene-aware keyframes fused with a timestamped transcript, processed 100% locally (ffmpeg + Whisper), cached per source. Requires Python 3.10+ and ffmpeg; runs via uvx from PyPI (claude-real-video).

MCP server to download YouTube audio & search videos — via Docker or npx. Powered by yt-dlp and ffmpeg.

Convert, resize, crop, filter & composite images locally — a tiny, no-dependency CLI with an ffmpeg-style filtergraph. Runs on your machine, so it works on your own image files.

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

Your agent cannot listen to audio. harken fixes that — locally. MCP server + CLI, one 13 MB binary, fully offline: no Python, no ffmpeg, no API key.

Free video editing engine for AI agents: cut, caption and render short-form video locally with FFmpeg, and reuse a viral video's format as a template. CLI and MCP server.

Local speech-to-text for macOS (CLI + MCP) — whisper.cpp statically linked against Metal, so no API key, no ffmpeg, and no audio leaving the machine. Defaults to large-v3-turbo, measured on-machine to beat the Japanese-specialised alternative even on Japanese; VAD gating suppresses hallucinations over silence

Download, transcribe, and get metadata for any video or audio URL — YouTube, TikTok, X, podcasts, and 1000+ other sites. Importly runs yt-dlp, rotating residential proxies, ffmpeg, and speech-to-text server-side, so your agent never deals with IP bans, 429s, or extractor breakage. **Tools:** `import_media`/`check_import` (download to hosted storage), `transcribe_media`/`check_transcription` (timestamped transcripts), `get_metadata`/`check_metadata`, `get_basic_metadata`/`check_basic_metadata`, `check_balance`. Get a free API key with **$3.00 in credits (no card required)** at [importly.io](https://importly.io/?utm_source=mcp&utm_medium=integration&utm_campaign=smithery). Setup guide: [importly.io/docs/integrations/mcp](https://importly.io/docs/integrations/mcp?utm_source=mcp&utm_medium=integration&utm_campaign=smithery)

MCP server that turns any video (local file or URL) into frames + transcript for Claude.

Turn a screen recording into annotated keyframes a coding agent can read. MCP server + CLI.

MCP server with 90 local multimedia tools — PDF, image, audio, video, Office, PII redaction

DeepSeek Harness 本地视频制作与设计插件：多轨剪辑、模板与设计体系、原生预览画布和真实文件导出

Turn a screen recording into annotated keyframes a coding agent can read. MCP server + CLI.

A video editor an AI agent drives, running on your own machine.

Let any LLM watch a video: scene-aware keyframes, storyboards, and timestamped transcripts, via MCP or any provider's API.