“video”

Compatibility package: mcp-video now installs Kinocut (formerly mcp-video).

Let any LLM watch a video locally — and search everything it has ever watched.

SVG to Video

GehDoc

Convert animated SVG (CSS/SMIL) to video (MP4/WebM) or image (GIF/aPNG) with in-band delivery.

Guardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.

Download any video from a URL, or get its transcript and key frames.

MCP server that lets image-only models look at video: timecoded frames, measurable properties.

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

Script to finished Bilibili video with Huasheng: storyboard, narration, footage, export, publish.

Bilibili MCP tool for video metadata, transcripts, subtitles, and comment summarization

Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.

Analyze YouTube/TikTok/Instagram videos: transcripts, AI insights, tutorial extraction

Upscale, stabilize, denoise and raise the frame rate of videos locally on your NVIDIA GPU

Animated b-roll overlays for short-form video.

Video Editing Ai MCP server.

Analyze videos: extract frames, transcribe audio, generate storyboard breakdowns.

Local videos or YouTube/Bilibili URLs -> timestamped transcript, keyframes, contact sheets.

Visual Memory MCP

putervision

Local visual UI cache for AI agents using perceptual hashing, CLIP, and 3D spatial grounding.

Generate AI images and videos, estimate credits and track tasks.

4K video generation via Google VEO 3.1: text-to-video, image-to-video, video extension

Drive Google Flow from an agent: Veo video and Imagen image generation

Woven

woven-video

Make and edit videos in Woven, the AI video editor for Mac.

Read videos like images: index once locally, query the text layer, fetch frames on demand.

Shrink video files on your Windows PC with H.265/AV1 and GPU encoding, a whole folder at a time

MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.