FFmpeg MCP Server for Zed: Video Processing in Your AI Editor

#mcp #zed #ffmpeg #ai

Originally published at ffmpeg-micro.com

Zed is a fast, Rust-native code editor with built-in MCP support. Connect the FFmpeg Micro MCP server and you can process video by typing a prompt in the AI assistant. No terminal switching, no curl commands to construct, no API docs to keep open in another tab.

Set up FFmpeg Micro MCP in Zed (2 minutes)

You need two things: a free FFmpeg Micro API key (grab one at ffmpeg-micro.com) and Zed installed.

Add the MCP server to Zed settings

Open Zed settings with Zed > Settings (or Cmd+, on macOS). Add the context_servers block:

{
  "context_servers": {
    "ffmpeg-micro": {
      "command": {
        "path": "npx",
        "args": ["-y", "@ffmpeg-micro/mcp-server"],
        "env": {
          "FFMPEG_MICRO_API_KEY": "your_api_key_here"
        }
      }
    }
  }
}

Replace your_api_key_here with your actual API key and save the file.

What the MCP server exposes

Once connected, Zed AI assistant can call these tools:

create_transcode converts video between formats
get_transcode checks job status
list_transcodes shows recent processing history
create_presigned_url generates upload URLs
confirm_upload verifies file upload
get_download_url gets signed download link
transcribe_audio generates SRT subtitles using Whisper

Real examples

Convert MP4 to WebM:

"Convert this video to WebM at high quality: https://storage.example.com/demo.mp4"

Resize for Instagram Reels:

"Make this video vertical 1080x1920 for Instagram: https://storage.example.com/landscape.mp4"

Extract audio as WAV:

"Pull just the audio from this video as WAV: https://storage.example.com/interview.mp4"

Why Zed for video processing

Speed. Zed is written in Rust. The editor stays responsive while MCP tools run.
Native MCP support. Built into Zed core, not an extension.
Context awareness. The assistant reads your open files and project context.
Minimal setup. One JSON block in settings, one API key.