Kinocut MCP server

Read from the package source without running it. The installed server may list more.

• async_wrapper
• audio_compose

  Layer multiple audio tracks with volume mixing.

• audio_effects

  Apply audio effects chain to a WAV file.

• audio_preset

  Generate preset sound design elements.

• audio_sequence

  Compose multiple audio events into a timed sequence.

• audio_synthesize

  Generate audio procedurally using synthesis.

• effect_chromatic_aberration

  Apply chromatic aberration - RGB channel separation.

• effect_glow

  Apply bloom/glow effect for highlights.

• effect_noise

  Apply film grain or digital noise.

• effect_scanlines

  Apply CRT-style scanlines overlay.

• effect_vignette

  Apply vignette effect - darkened edges.

• glitch_cmyk_split

  Apply CMYK split glitch effect.

• glitch_datamoshing

  Apply datamoshing glitch effect.

• glitch_depth_splatting

  Apply depth-based point splatting effect (requires Node.js + GPU).

• glitch_digital_feedback

  Apply digital feedback glitch effect (requires Node.js + GPU).

• glitch_macroblocking

  Apply macroblocking glitch effect.

• glitch_point_cloud

  Apply point cloud rendering effect (requires Node.js + GPU).

• glitch_rgb_shift

  Apply RGB channel shift glitch effect.

• glitch_scanline_jitter

  Apply scanline jitter glitch effect.

• glitch_screen_tearing

  Apply screen tearing glitch effect.

• glitch_slit_scan

  Apply slit-scan temporal displacement effect (requires Node.js + GPU).

• glitch_turbulent_displacement

  Apply turbulent displacement glitch effect.

• glitch_vhs_tracking

  Apply VHS tracking error glitch effect.

• hyperframes_catalog

  Browse Hyperframes catalog blocks/components.

• hyperframes_compositions

  List compositions in a Hyperframes project.

• hyperframes_info

  Print Hyperframes project metadata.

• hyperframes_inspect

  Inspect rendered composition layout for overflow and visual issues.

• hyperframes_preview

  Launch Hyperframes preview studio for live preview.

• hyperframes_render

  Render a Hyperframes composition to video.

• hyperframes_snapshot

  Capture key frames as PNG screenshots for visual verification.

• hyperframes_still

  Render a single frame as image from a Hyperframes composition.

• search_tools

  Find registered MCP tools by name, keyword, or a supported task phrase.

• shot_prompt_render

  Expand one storyboard shot into prompt and negative_prompt strings.

• storyboard_read

  Read a PUSHING CREATION storyboard table from storyboard.md or a project directory.

• style_pack_read

  Read STYLE_ and NEG_ blocks from a style.md file or project directory.

• transition_glitch

  Apply glitch transition between two video clips.

• transition_morph

  Apply morph transition between two video clips.

• transition_pixelate

  Apply pixelate transition between two video clips.

• video_acceptance_eval

  Evaluate exact-spec verdict and defect evidence without approving anything.

• video_add_audio

  Add, replace, or mix an audio track into a video.

• video_add_generated_audio

  Add procedurally generated audio to a video.

• video_add_text

  Overlay text on a video (titles, captions, watermarks). Returns JSON {success, output_path}. Use to burn a single text element into a video. Pass input_path as the source video, text with the string to draw, and position/size/color to style it; output_path is auto-named when omitted.

• video_add_texts

  Overlay multiple text elements on a video in a single FFmpeg pass.

• video_ai_color_grade

  Apply a color grade to a video — by LUT file, style preset, or reference video.

• video_ai_remove_silencewrite action

  Remove silent sections from video.

• video_ai_scene_detect

  Detect scene changes in video.

• video_ai_stem_separation

  Separate audio into stems using Demucs.

• video_ai_transcribe

  Transcribe speech to text using Whisper.

• video_ai_upscale

  Upscale video using AI super-resolution.

• video_analyze

  Comprehensive video analysis — transcript, metadata, scenes, audio, quality, chapters, colors.

• video_apply_mask

  Apply an image mask to a video with edge feathering.

• video_audio_bed

  Mix a looped music bed under a voice source with ducking and loudness normalization.

• video_audio_spatial

  Apply 3D spatial audio positioning.

• video_audio_waveform

  Extract audio waveform data (peaks and silence regions).

• video_auto_chapters

  Auto-detect scene changes and create chapters.

• video_batch

  Apply the same operation to multiple video files.

• video_body_swap

  Replace video while preserving approved audio with explicit duration policy.

• video_chroma_keywrite action

  Remove a solid color background (green screen / chroma key).

• video_cleanupwrite action

  Delete intermediate video files after a workflow.

• video_compare_quality

  Compare video quality between original and processed versions.

• video_composite_layers

  Composite ordered image/video layers from a JSON spec.

• video_convert

  Convert a video to a different format or codec.

• video_create_from_imageswrite action

  Create a frame-exact video from a sequence of images.

• video_design_quality_checkwrite action

  Run comprehensive design quality analysis on a video.

• video_detect_scenes

  Detect scene changes in a video.

• video_duck_audio

  Mix background music under a video's voice with automatic ducking.

• video_export_frames

  Export frames from a video as individual images.

• video_extract_frame

  Extract a frame using the same sampling as CLI and Python frame extraction.

• video_filter

  Apply a visual filter to a video.

• video_fix_design_issues

  Auto-fix design issues in a video.

• video_generate_subtitles

  Generate SRT subtitles from text entries and optionally burn into video.

• video_hls_segment

  Segment a video into HLS (HTTP Live Streaming) format.

• video_info

  Probe a video file for metadata. Returns JSON {success, info:{duration, resolution, codec, fps, size, ...}}. Use before any edit to learn the source's dimensions and length. Pass input_path as the absolute path to the existing video.

• video_info_detailed

  Get extended video metadata.

• video_layout_gridwrite action

  Create grid-based multi-video layout.

• video_layout_pip

  Picture-in-picture overlay.

• video_luma_key

  Mask out dark regions based on luminance (brightness).

• video_merge

  Merge multiple video clips into one rendered output file.

• video_mix_audio

  Mix timed sounds with one AAC encode and stream-copy the primary picture.

• video_mograph_count

  Generate animated number counter video.

• video_mograph_progress

  Generate progress bar / loading animation.

• video_normalize_audio

  Normalize audio loudness to a target LUFS level.

• video_overlay

  Picture-in-picture: overlay a video on top of another.

• video_project_createwrite action

  Scaffold a cinematic video project with style, storyboard, and refs folders.

• video_quality_checkwrite action

  Run visual quality checks on a video.

• video_read_metadata

  Read metadata tags from a video/audio file.

• video_release_checkpointwrite action

  Create preview artifacts only after the video passes quality gates.

• video_resize

  Resize a video or change its aspect ratio. Returns JSON {success, output_path}. Use to fit a video to target dimensions or a preset ratio. Pass input_path as the source video (e.g. from video_info) and either width/height or aspect_ratio to define the target.

• video_reverse

  Reverse video and audio playback so it plays backwards.

• video_salvagewrite action

  Create one lineage-bound salvage derivative and a fresh review slot.

• video_shape_mask

  Apply a geometric shape mask to a video.

• video_speed

  Change video playback speed and render a new output file.

• video_split_screen

  Place two videos side by side or top/bottom.

• video_stabilize

  Stabilize a shaky video using motion vector analysis.

• video_subtitles_styled

  Burn subtitles from SRT/VTT with custom styling.

• video_text_animated

  Add animated text to video.

• video_trim

  Trim a video clip by start time and duration. Returns JSON {success, output_path} pointing at the rendered clip. Use to cut a segment out of a longer video. Pass input_path as the absolute path to the source video (e.g. from video_info), start as a timestamp, and duration or end to define the segment.

• video_validate_text_layout

  Validate a set of text overlays for visual failure modes before rendering.

• video_verdict

  Persist exact-asset analysis; approvals require active human evidence.

• video_write_metadatawrite action

  Write metadata tags to a video/audio file.

• Code scan674 source files scanned20/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 1 days ago15/15
• Maintainer identityregistry namespace matches repository owner7/10

Safety score

83/100

higher than 70% of 1,240 Media servers

Tools

100

the typical Media server has 7

Tools that change things

11%

typical: 5%. Fewer write tools means less an agent can break

GitHub stars

221

more than 95% of 680 Media servers

Downloads a week

4,545

more than 96% of 335 Media servers with a package

Kinocut: common questions

Is Kinocut MCP server safe?

Mostly: it is graded B (83/100). Read the Kinocut safety report

How do I install Kinocut?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Kinocut need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Kinocut maintained?

The last commit was in the last day (2026-10-24). The latest release is v1.16.4.

What can I use instead of Kinocut?

Servers from other publishers that do the same job: CartCut MCP server, Rendobar MCP server and FFmpeg MCP server. Compare all Kinocut alternatives.

How does Kinocut compare with other Media MCP servers?

safety score 83/100 (higher than 70% of 1,240 Media servers); tools 100 (the typical Media server has 7); tools that change things 11% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.