ffmpeg-mcp-lite: Skill for Claude Code

.claude/skills/mcp-builder/SKILL.md

mcp-builder is a skill for Claude Code from kevinwatt/ffmpeg-mcp-lite. It costs 0 tokens per session (1,313 once invoked), scanned A, original, MIT.

A development guide for ffmpeg-mcp-lite, an MCP server that uses FFmpeg to process video and audio files.

In plain words
What is it for?
Use it when developing or extending tools for reading media information, converting, compressing, trimming, merging, or extracting audio from files.
Why use it?
It gives contributors a shared description of the server’s technology choices, tool names, and supported operations.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is kevinwatt/ffmpeg-mcp-lite's own configuration. It tells Claude Code how to work on ffmpeg-mcp-lite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ffmpeg-mcp-lite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kevinwatt/ffmpeg-mcp-lite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/kevinwatt/ffmpeg-mcp-lite/main/.claude/skills/mcp-builder/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kevinwatt/ffmpeg-mcp-lite

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinwatt/ffmpeg-mcp-lite/mcp-builder/github.svg)](https://agentmods.dev/skills/kevinwatt/ffmpeg-mcp-lite/mcp-builder)
Your own site
<a href="https://agentmods.dev/skills/kevinwatt/ffmpeg-mcp-lite/mcp-builder"><img src="https://agentmods.dev/badge/skills/kevinwatt/ffmpeg-mcp-lite/mcp-builder/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/kevinwatt/ffmpeg-mcp-lite/mcp-builder"><img src="https://agentmods.dev/badge/skills/kevinwatt/ffmpeg-mcp-lite/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,313 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01313
Opus 5 $0.00000 $0.00656
Sonnet 5 $0.00000 $0.00263
Haiku 4.5 $0.00000 $0.00131

Measured 10d ago against content hash 720cb87ed43a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-builder scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

stdout=asyncio.subprocess.PIPE,
.claude/skills/mcp-builder/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FFmpeg MCP Server Development Guide

Overview

This skill guides the development of ffmpeg-mcp-lite, an MCP server that provides video and audio processing capabilities through FFmpeg.

Repository: https://github.com/kevinwatt/ffmpeg-mcp-lite PyPI: https://pypi.org/project/ffmpeg-mcp-lite/


Project Specifications

Technology Stack

  • Language: Python 3.10+
  • Framework: FastMCP (from mcp package)
  • Package Manager: uv
  • CLI Tool: FFmpeg / FFprobe

Tool Naming Convention

All tools use ffmpeg_ prefix to avoid conflicts with other MCP servers.


Implemented Tools

Core Tools

Tool Description Parameters
ffmpeg_get_info Get video/audio metadata file_path
ffmpeg_convert Convert format (with optional scale) file_path, output_format, scale?, video_codec?, audio_codec?
ffmpeg_compress Compress video (with optional scale) file_path, quality, scale?, preset?
ffmpeg_trim Trim video segment file_path, start_time, end_time?, duration?
ffmpeg_extract_audio Extract audio track file_path, audio_format, bitrate?
ffmpeg_merge Concatenate videos file_paths, output_path?
ffmpeg_extract_frames Extract frames as images file_path, interval?, count?, format?
ffmpeg_add_subtitles Burn-in subtitles to video file_path, subtitle_path, style?, font_size?, output_path?

Project Structure

ffmpeg-mcp-lite/
├── src/ffmpeg_mcp/
│   ├── __init__.py
│   ├── __main__.py
│   ├── server.py          # MCP server core
│   ├── config.py          # Configuration
│   └── tools/
│       ├── __init__.py
│       ├── info.py        # ffmpeg_get_info
│       ├── convert.py     # ffmpeg_convert
│       ├── compress.py    # ffmpeg_compress
│       ├── trim.py        # ffmpeg_trim
│       ├── audio.py       # ffmpeg_extract_audio
│       ├── merge.py       # ffmpeg_merge
│       ├── frames.py      # ffmpeg_extract_frames
│       └── subtitles.py   # ffmpeg_add_subtitles
├── tests/
│   ├── conftest.py
│   ├── test_info.py
│   ├── test_convert.py
│   ├── test_compress.py
│   ├── test_trim.py
│   ├── test_audio.py
│   ├── test_merge.py
│   ├── test_frames.py
│   └── test_subtitles.py
├── pyproject.toml
├── README.md
├── CLAUDE.md
└── LICENSE

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 189 lines · 0 tokens per session scan A 720cb87ed43a

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository kevinwatt/ffmpeg-mcp-lite (26 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,313 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

c-video

Download videos, extract audio, convert formats, and clip segments using yt-dlp and ffmpeg. Supports YouTube, Vimeo, and hundreds of other sites.

daxaur/openpaw · 38 tokens

loudcheck

Loudness compliance verdicts against formal published standards — EBU R 128, ATSC A/85, or BS.1770 measure-only. Use it when audio or video has to pass a delivery gate: "is this file broadcast-legal?", "will this mix get rejected?", "how far off target is it and what's the exact fix?", batch-checking a delivery…

chaoz23/loudcheck · 109 tokens

video-editing

Operate Video Agent Runtime projects through structured MCP tools for transcript-first long-form-to-short-form editing, preview review, feedback diagnosis, narration, versioning, and approved export. Use for editing an existing runtime project; do not use for direct FFmpeg or manual project-JSON changes.

YansIlinta/video-agent-runtime · 60 tokens

apollo-onboarding

Plans and configures a Universal Audio Apollo rig end to end through the uad-console-mcp MCP server, covering the interview questions to ask, which physical input suits which source, the clock master decision for ADAT expanders and other digital gear, ADAT sample-rate and channel-count limits, multi-Apollo Thunderbolt…

fomoPhil/uad-console-mcp · 183 tokens

Ferramenta Python de Divisão de Áudio com GUI e FFmpeg Local

Cria um script Python completo com interface gráfica (Tkinter) para dividir arquivos de áudio em segmentos, utilizando um executável FFmpeg localizado na mesma pasta do script.

ECNU-ICALK/AutoSkill · 51 tokens

vidgrid

Give an AI agent eyes for video. Turn a local video file (MP4, MOV, WebM) into a numbered grid of frames plus a transcript that a vision model can read — so you can summarize a talk, find the exact moment something happens, read on-screen text or UI, or rank clips. Use whenever you need to watch, analyze, or…

pawvej/vidgrid · 85 tokens