Ffmpeg MCP Server

`ffmpeg-mcp` is a [Model Context Protocol](https://modelcontextprotocol.io) server that puts the full power of **FFmpeg** behind a clean set of tools

Local serverstdioPython

What is the Ffmpeg MCP MCP server?

Ffmpeg MCP MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. ffmpeg-mcp is a Model Context Protocol server that puts the full power of FFmpeg behind a clean set of tools your LLM can call — clip, crop, scale, overlay, concatenate with transitions, extract.

What the assistant can call

Once Ffmpeg MCP is connected, these are the calls the assistant has available:

  • get_video_metadata — Probe a file for streams, codecs, duration, etc
  • extract_frames — Save frames as images (evenly, by interval, or 1/sec)
  • extract_audio — Pull audio out to a .wav file
  • scale_video — Upscale to 1080p / 2k / 4k, aspect-preserving
  • crop_video — Crop to a region
  • clip_video — Cut a sub-clip by start + duration
  • make_gif — Turn a segment into an optimized GIF
  • overlay_image — Composite an image (logo/watermark) with timing & opacity
  • overlays_video — Overlay a (looping) video onto another
  • trim_and_concat_operation — Trim multiple clips and stitch them together
  • get_normalized_clips — Normalize clips to a common res/fps/codec (in parallel)
  • concat_clips_with_transition — Concatenate clips with an xfade transition

Configuration and credentials

You will need one environment variable: PYTHONPATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Choosing this one

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Ffmpeg MCP's toolset — get_video_metadata, extract_frames, extract_audio and 9 more — is a fair guide to whether it matches your workflow. It is maintained by yubraaj11; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Ffmpeg MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the ffmpeg mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
get_video_metadataProbe a file for streams, codecs, duration, etc.
extract_framesSave frames as images (evenly, by interval, or 1/sec)
extract_audioPull audio out to a .wav file
scale_videoUpscale to 1080p / 2k / 4k, aspect-preserving
crop_videoCrop to a region
clip_videoCut a sub-clip by start + duration
make_gifTurn a segment into an optimized GIF
overlay_imageComposite an image (logo/watermark) with timing & opacity
overlays_videoOverlay a (looping) video onto another
trim_and_concat_operationTrim multiple clips and stitch them together
get_normalized_clipsNormalize clips to a common res/fps/codec (in parallel)
concat_clips_with_transitionConcatenate clips with an xfade transition

Configuration

VariableDescriptionRequired
PYTHONPATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Ffmpeg MCP to get video metadata.
  • Use Ffmpeg MCP to extract frames.
  • Use Ffmpeg MCP to extract audio.

Frequently asked questions

It connects Ffmpeg MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (get_video_metadata, extract_frames, extract_audio, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Ffmpeg MCP directly.