Rust MCP server and CLI for yt-dlp search, downloads, metadata, transfers, and Plex playlists.
Provider-neutral CLI and MCP server for short-form AI video with dry-run validation and optional live generation.
Key Features: Dry-run mode for safe payload validation without API calls Supports multiple providers: Sora/OpenAI, Gemini Veo, xAI/Grok, Seedance/PiAPI CLI commands for manifest, doctor, privacy audit, payload generation Omnimodal MCP server converting ComfyUI workflows into tools for text, image, sound, and video generation with web UI.
Key Features: Full-modal support for text, image, sound, and video generation Dual execution modes: local ComfyUI and RunningHub cloud service Zero-code workflow-to-MCP tool conversion Convert HTML slide carousels to PNG, WebP, PDF, or PPTX with themed templates and Puppeteer rendering.
Key Features: Render slides to PNG, WebP, PDF, and PPTX Supports 7 distinct slide themes with design system styles Dimension-aware reflow for portrait and landscape layouts Locally process video or audio into timestamped transcripts, speakers, scenes, chapters, OCR, and searchable timeline data for AI agents.
Key Features: Word-level transcripts in approximately 100 languages Speaker diarization with local processing Scene detection and per-scene keyframes Let any LLM actually watch a video: scene-aware keyframes plus a timestamped transcript, local.
Transforms vague prompts into platform-optimized prompts for 60+ AI platforms across 7 categories.
Key Features: Context-aware prompt optimization for 60+ platforms Supports 7 AI categories: image, video, voice, music, code, chat, document Custom platform registration and management Hosted media-generation MCP server for images, video, audio, transcription, and multi-step workflows via OAuth.
Key Features: Streamable HTTP JSON-RPC 2.0 API OAuth 2.1 authentication with dynamic client registration Multi-modal media generation (image, video, audio) Analyzes videos from URLs or local files to extract transcripts, key frames, OCR text, and annotated timelines without authentication.
Key Features: Supports major platforms: YouTube, Vimeo, TikTok, Instagram, X, Twitch, Dailymotion, Facebook, Loom Processes direct video URLs and local video files Extracts transcripts, key frames, OCR text, and metadata Scores AI image/video generation prompts and creatives against proven winning ads before spending generation credits.
Key Features: Scores prompts on a 0-100 scale against 18 models including Veo 3, Sora, Kling, and Midjourney Scores creatives by embedding and nearest neighbor search against 800+ winning ads Provides enhancement briefs for prompt rewriting based on real market lift data MCP server for generating and editing images and videos via OpenRouter or OpenAI-compatible APIs with file saving and previews.
Key Features: Text-to-image generation with multiple variations and aspect ratios Image editing supporting local files, URLs, and compositing Text-to-video and image-to-video generation with resumable jobs Local-first video editing MCP server with typed FFmpeg tools, captions, effects, quality gates, and provenance receipts.
Key Features: Typed FFmpeg-based video editing tools Video Receipts for provenance and auditability Quality gates and release checkpoints 