Skip to main content
Glama
Sign In
video-editor-mcp

video-editor-mcp

by chevrolet231X
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

video-editor-mcp

An MCP (Model Context Protocol) server that gives Claude (or any MCP-compatible client) real video-editing tools, powered by ffmpeg. Once connected, you can ask Claude things like "trim intro.mp4 to the first 10 seconds, add my logo in the corner, and export it as a GIF" and it will call these tools directly.

Requirements

  • Node.js 18+

  • ffmpeg and ffprobe installed and available on your system PATH

Related MCP server: ffmpeg-mcp

Install

cd video-editor-mcp
npm install

Configure where your videos live

Every tool takes file paths. Relative paths are resolved against the MEDIA_DIR environment variable (so Claude doesn't need to know your full filesystem layout) — set it to the folder containing the videos you want to edit. Absolute paths are always used as-is. If MEDIA_DIR isn't set, it defaults to the directory you launch the server from.

Connect it to an MCP client

This is a standard MCP server using the stdio transport, so any MCP-compatible client/host can spawn and talk to it. The host just needs to launch this process and communicate over stdin/stdout:

  • Command: node

  • Args: ["/absolute/path/to/video-editor-mcp/src/index.js"]

  • Env: MEDIA_DIR=/absolute/path/to/your/videos

How you wire that up depends on your host/client's own configuration format (most MCP-aware hosts use a command + args + env shape similar to the above).

Tools exposed

Tool

What it does

get_media_info

Duration, resolution, codecs, fps, bitrate, file size

trim_video

Cut a clip by start time + end time/duration

merge_videos

Concatenate multiple clips into one (auto-normalizes resolution)

convert_format

Change container/codec (mp4, mov, webm, mp3, etc.)

extract_audio

Pull the audio track out as an MP3

resize_video

Scale to a target width/height

crop_video

Crop to a rectangular region

rotate_video

Rotate 90/180/270° and/or flip horizontally/vertically

change_speed

Speed up or slow down (pitch-corrected audio)

adjust_volume

Raise/lower volume, or mute

extract_frame

Grab a still frame at a timestamp

add_text_overlay

Burn in a caption/title, optionally timed

add_watermark

Overlay a logo image at a chosen corner

add_fade

Fade in/out (video, audio, or both)

compress_video

Re-encode at a target quality (CRF) to shrink file size

generate_gif

Convert a video segment into an animated GIF

Each tool returns the resulting file's path and size, so Claude can chain operations (e.g. trim → add watermark → compress) by feeding one tool's output into the next tool's input.

Testing without Claude

Run the unit tests, which generate a synthetic test video with ffmpeg and exercise every operation:

npm test

Run a full protocol-level test (spins up the server and a real MCP client, lists tools, and calls a couple of them):

node test/e2e-client.js

(The e2e test expects npm test to have been run first so test/tmp/v1.mp4 exists — or generate your own test clip there.)

Notes & limitations

  • All operations re-encode by default for correctness (frame-accurate trims, mixed-codec merges, etc.) rather than using fast -c copy cuts, so they're not the fastest possible, but they're reliable across arbitrary inputs.

  • This server runs entirely on your local machine and only touches files you point it at — no video data is uploaded anywhere.

  • There's no built-in sandboxing beyond the MEDIA_DIR convenience for relative paths; since the server has the same filesystem permissions as whatever process launches it, only connect it to clients you trust.

Available Tools

16 tools
add_fadeB

Add a fade-in and/or fade-out to a video, audio, or both.

Inputs: input_path (required), output_path (required), target, fade_in_duration, +1 more.

add_text_overlayA

Burn text (e.g. a caption or title) onto a video, optionally only during a time range.

Inputs: text (required), input_path (required), output_path (required), end_time, +4 more.

add_watermarkC

Overlay a logo/watermark image onto a video at a chosen corner or the center.

Inputs: input_path (required), output_path (required), watermark_path (required), opacity, +2 more.

adjust_volumeA

Change the audio volume of a video, or mute it entirely.

Inputs: input_path (required), output_path (required), mute, volume_factor.

change_speedA

Speed up or slow down a video (audio pitch is preserved). speed_factor > 1 speeds up, < 1 slows down (e.g. 2 = 2x faster, 0.5 = half speed).

Inputs: input_path (required), output_path (required), speed_factor (required).

compress_videoA

Reduce a video file size by re-encoding it with a given quality level (CRF). Lower CRF = higher quality/larger file; higher CRF = smaller file/lower quality. 28 is a reasonable default.

Inputs: input_path (required), output_path (required), crf, preset.

convert_formatA

Convert a video/audio file to a different container/codec. The output format is inferred from the output_path extension (e.g. .mp4, .mov, .webm, .avi, .mp3).

Inputs: input_path (required), output_path (required).

crop_videoC

Crop a video to a rectangular region.

Inputs: width (required), height (required), input_path (required), output_path (required), +2 more.

extract_audioA

Extract the audio track from a video file and save it as an MP3.

Inputs: input_path (required), output_path (required).

extract_frameA

Grab a single still frame from a video at a given timestamp and save it as an image.

Inputs: input_path (required), output_path (required), timestamp.

generate_gifB

Convert a segment of a video into an animated GIF.

Inputs: input_path (required), output_path (required), fps, width, +2 more.

get_media_infoA

Inspect a video or audio file: duration, resolution, codecs, fps, bitrate, file size.

Inputs: input_path (required).

merge_videosA

Concatenate two or more video files into one, in the given order. Clips are auto-scaled to match so different resolutions/codecs can be joined.

Inputs: input_paths (required), output_path (required).

resize_videoA

Resize/scale a video. Provide width, height, or both (aspect ratio is preserved if only one is given).

Inputs: input_path (required), output_path (required), width, height.

rotate_videoB

Rotate and/or flip a video.

Inputs: input_path (required), output_path (required), flip, rotation.

trim_videoA

Cut a clip out of a video between a start time and either an end time or a duration (seconds).

Inputs: input_path (required), output_path (required), duration, end_time, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.7/5.0

    Scored across 16 tools

    Disambiguation5/5

    Each tool targets a distinct video/audio editing operation with clear separation: inspecting, extracting, trimming, merging, converting, resizing, cropping, rotating, speed/volume changes, frame grabbing, overlays, fades, compression, and GIF generation. Even overlapping pairs like convert_format vs compress_video or extract_frame vs generate_gif have well-defined differences in purpose and output.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern using lowercase with underscores (get_media_info, extract_audio, trim_video, etc.). There are no mixed conventions, camelCase, or vague verbs, making the toolset highly predictable.

    Tool Count4/5

    With 16 tools, the set is slightly above the typical 3-15 sweet spot, but each tool serves a distinct common editing need. The count feels justified given the broad scope of video editing, though one or two could be consolidated (e.g., add_text_overlay and add_watermark are both overlays).

    Completeness4/5

    The toolset covers core video editing workflows: inspect, trim, merge, convert, transform (resize/crop/rotate), audio adjustment, frames, text/watermark overlays, fades, compression, and GIF export. Missing operations like video stabilization or color grading are minor gaps for a basic editor, and agents can accomplish most tasks without dead ends.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers