#ffmpeg

Podcli is an open-source MCP server and CLI that turns long-form podcasts into upload-ready short clips for TikTok, YouTube Shorts, and Reels. It transcribes with Whisper, finds viral moments with Claude or Codex against your show's knowledge base, crops to vertical with face tracking, and burns in captions in four styles. Ships 17 MCP tools you can plug into Claude Code, Claude Desktop, or Codex — ask the agent to "clip this episode" and it handles transcription, clip scoring, and export end to end. Runs fully locally, no uploads, no API keys required unless you opt into AI clip picking. MIT licensed.

An MCP server for FFmpeg

mcp-ffmpeg-tools is an open-source Python MCP (Model-Command Protocol) server that enables LLMs to perform media processing tasks by interpreting natural language instructions. It automatically generates and executes FFmpeg commands, then validates results using `ffprobe` or screenshots. The tool also supports querying FFmpeg source code to verify command correctness, making it ideal for intelligent, language-driven media workflows across platforms.