Media

Local AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.

MCP Server：用 MiniMax 多模态模型把图片解析成文字描述，供 DeepSeek 等纯文本模型使用

Turn a public video into an evidence table an LLM can read: timecoded transcript, sampling sheets and AudioSet sound events, downloading only the bytes it needs.

MCP server that bridges vision models to text-only coding models using Florence-2

Analyze any video (local file or URL) into frames + transcript for Claude Code

MCP Server for video processing - extract frames, metadata, audio and create GIFs

MCP server for comprehensive video analysis — transcription, AI-powered visual frame analysis, and metadata extraction

MCP server for advanced video editing: aspect ratio adjustment, subtitles, overlays, concatenation, speed changes, and transitions

Unified MCP server for video generation with intelligent HeyGen/Veo routing

MCP server for video format conversion and property adjustment using FFmpeg

MCP Server for Video Jungle - Analyze, Search, Generate, and Edit Videos

MCP server for video content extraction: audio extraction, video trimming, frame extraction, and scene detection

MCP server for video compression and optimization: bitrate, resolution, frame rate, and codec adjustment

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

把视频链接转成 GIF 动图的 MCP 服务 (含 SSRF 防护, 供魔搭/DEAP/Claude 等 MCP 客户端调用)

Video editing MCP server using FastMCP and ffmpeg-python

让 agent 驱动本机的 Verbatim 音视频转写与博主观点分析：提交转写、轮询、搜索转写库。

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

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

VAP MCP Server - Execution control layer for Claude Desktop and MCP clients