# ffmpeg-mcp

> Use this tool when you need to execute ffmpeg and ffprobe operations securely, avoiding shell injection vulnerabilities. It solves media processing problems such as video conversion, trimming, and watermarking, while providing a safe interface for passing arguments as arrays. Ideal for batch processing and automation tasks, it supports various operations including probe, concat, thumbnail, and loudnorm.

Canonical page: https://skillsregistry.net/skills/cudgk-ffmpeg-mcp  
JSON: https://api.skillsregistry.net/v1/skills/cudgk-ffmpeg-mcp

## Description

Enables LLMs to safely execute ffmpeg and ffprobe operations by passing arguments as arrays, avoiding shell injection, with support for probe, convert, trim, concat, thumbnail, watermark, speed, loudnorm, and batch processing.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/k4prvezwvk)
- **Repository:** <https://github.com/cUDGk/ffmpeg-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "cudgk-ffmpeg-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cudgk-ffmpeg-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cudgk-ffmpeg-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt