Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    VidMCP Video Editing

    1

    Let your AI agent actually edit video: denoise, add captions and music, replace backgrounds, cut fillers and export for Reels, YouTube or square in one call.

    Free

    2 usesSecurity scanned
    VidMCP Video Editing

    VidMCP Video Editing

    Example session with this skill installed

    Polish this raw footage 'intro.mp4' for Instagram Reels. Remove the background noise, add some space-themed background, cut out the filler words, and add captions.

    • Read your context and instructions
    • Compiled the vidmcp video editing

    I have processed 'intro.mp4' using the talking_head_reels recipe. The pipeline included audio denoising, smart cutting for hesitations, background replacement with a space theme, and caption generation.

    Video Processing Summary

    TaskTool UsedStatus
    Importimport_videoCompleted (intro.mp4)
    Audioprocess_audioDenoised & Normalized
    Cuttingsmart_cut_hesitations4 filler words removed
    Visualsreplace_backgroundMode: Space
    Texttranscribe_and_captionBurned-in captions added
    Exportexport_renderPreset: reels_9x16

    The final render is available at /workspaces/project_01/exports/intro_reels_space.mp4.

    Next steps

    • Preview the export to ensure the space background alignment is correct.
    • If the background music is too loud, I can re-run mix_bgm with a lower volume offset.
    • I can generate a youtube_16x9 version if you want to post the full length version.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Agents don't describe video. They cut it.

    VidMCP Video Editing teaches your agent to drive the open source VidMCP MCP server (MIT licensed, by Dhiraj Lochib) for real talking-head video editing.

    What your agent can do

    • One-call talking-head polish: orient, denoise, background music, captions, optional background replace, export
    • Audio cleanup: denoise, gate, EQ, loudness normalization, music ducking under voice
    • Whisper captions with brand burn-in
    • Background replacement behind the subject (space, blur or solid plate)
    • Dead air and filler word removal
    • Export presets: YouTube 16:9, Reels 9:16, Square 1:1
    • Free text requests like "polish this talk for reels, space bg, cut fillers"

    Built for small agent context

    Only a compact tool pack is loaded by default and results are size capped, so your agent does not drown in tool schemas.

    Requirements

    Python 3.11+, ffmpeg and uv. Install with uv tool install vidmcp, then add the MCP server to your agent. Full setup steps are inside the skill.

    Source: https://github.com/dhirajlochib/VidMcp | Site: https://vidmcp.com

    Requires local VidMCP server and ffmpeg installation. Subject matting requires specific backends (MLX/mock). Portrait rotation is baked upright on import.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    • Free with an Agensi account

    Software
    Pythonuv (Python tool runner)

    Permissions

    Network Access
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard AI agents that only write scripts, this skill provides a direct interface to the VidMCP server, allowing the agent to physically manipulate video files, remove filler words, and apply visual effects through automated ffmpeg pipelines.

    This skill is designed for any AI agent or framework compatible with the Model Context Protocol (MCP). It requires Python 3.11+, ffmpeg, and the VidMCP server installed on your local machine or server.

    The skill includes high-level 'recipes' for common tasks like talking head polishing, automated captioning, and background replacement, along with specific tool schemas that allow your agent to execute complex post-production workflows.

    Yes, it includes specialized presets such as 'reels_9x16' that allow your agent to automatically crop, format, and add captions to horizontal footage for use on platforms like TikTok, Instagram Reels, and YouTube Shorts.

    While the core editing functions are universal, advanced features like subject matting (background removal) can leverage MLX backends for optimized performance on Apple Silicon hardware.

    The skill handles the heavy lifting of post-production, but it is designed with a 'human-in-the-loop' approach, requiring user confirmation before the final export render is triggered to ensure quality.

    New in Marketing & SEO

    Free