Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agentsffmpeg media
Automate local video and audio manipulation using the FFmpeg MCP server.
Free
ffmpeg media
Example session with this skill installed
Cut the video at workspace/recordings/demo.mp4 from 00:00:10 to 00:00:45 and save it as workspace/edits/clip.mp4. Create the output folder if needed.
- Read your context and instructions
- Compiled the ffmpeg media
I will process the video cut for you. First, I am creating the workspace/edits/ directory, then I will use the cut_video tool to extract the requested segment from demo.mp4.
Media Processing Task
| Parameter | Value |
|---|---|
| Tool Used | cut_video |
| Source Path | workspace/recordings/demo.mp4 |
| Output Path | workspace/edits/clip.mp4 |
| Start Time | 00:00:10 |
| End Time | 00:00:45 |
| Status | Completed |
# Log of MCP Tool Invocation
# 1. create_directory(path="workspace/edits")
# 2. cut_video(input_path="workspace/recordings/demo.mp4",
# output_path="workspace/edits/clip.mp4",
# start="00:00:10",
# end="00:45")
The video has been successfully trimmed. The original file remains untouched in the recordings folder.
Next steps
- Verify the playback of
workspace/edits/clip.mp4. - Convert the output to another format if required.
- Delete the source file if it is no longer needed for your project.
Connects securely to your tools. The creator never sees your data.
About this skill
Local media processing often requires memorizing complex CLI flags or fighting with GUI tools that bloat your system. This skill handles FFmpeg operations through a dedicated MCP server to manipulate files directly in your workspace.
What it does
- Video trimming uses the
cut_videotool to extract specific segments based on timestamps. - Media concatenation joins multiple video files into a single sequence via
concat_videos. - Format conversion changes audio or video containers based on file extensions.
- Still-to-video generation creates video files from static images with fixed durations.
- Silence removal automatically strips quiet sections from audio-heavy video tracks.
How it works
- Source identification identifies the local media files located within the
FFMPEG_MCP_WORKSPACE. - Parameter validation confirms the output paths and required timing or duration details before execution.
- Directory management creates necessary output folders to ensure write operations do not fail.
- Tool execution invokes specific FFmpeg functions or uses
ffmpeg_rawfor restricted custom arguments.
Frameworks & tools
This skill uses the FFmpeg MCP server. It interacts with local media files using specific tools like cut_video, concat_videos, and remove_silence.
Why this beats prompting it yourself
Generic prompts often hallucinate FFmpeg flags that do not work with specific MCP tool constraints. This skill is hard-coded to follow workspace path rules and uses dedicated methods for joining or cutting to prevent command-line syntax errors.
Use cases
- Convert a batch of
.movfiles to compressed.mp4for web hosting. - Trim the first and last 10 seconds off a recorded meeting.
- Create a 30-second video from a project logo for a social media background.
- Remove dead air from a podcast recording or technical demo.
Known limitations
Files must be within the FFMPEG_MCP_WORKSPACE. Raw command execution is restricted to local arguments and does not support external URLs or complex filter graphs.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 2 days ago
- Free to download with an account
Requires
Node.js
Git