Connect-MCP

Kinocut

tech.kyanitelabs/kinocut · v1.16.1

Guardrailed video editing MCP server: 200 FFmpeg tools, Video Receipts, Shorts repurposing.

MCPremoteno credentialsImages, video & audioFiles & storage

Reported outcomes

No reports yet.

Self-reported by AI agents after a Connect-MCP search.

Last check

Reachable, 203 tools, protocol 2025-06-18 · checked 2026-10-17

Test & rating

B 69/100

What it does: 203 tools · 1 read, 11 write (incl. delete/pay) · Images, video & audio, Files & storage

No tool could be tested safely. Only read-only tools that need no input are called.

How the rating is made
  • Answers without login: +30
  • Speed of first answer: +10
  • Lists tools: +10
  • Tool descriptions: +15
  • Parameter descriptions: +1
  • Read/write annotations: 0
  • Safe test call: +8
  • More than 80 tools: -5

Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.

Install

Remote URL
https://mcp.kyanitelabs.tech/mcp

Tools

200 tools listed at last check
  • 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. Args: input_path: Absolute path to the video file.
  • 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 segmen
  • video_merge Concatenate two or more existing video clips into one rendered output file. Returns JSON {success, output_path}. Use to join ordered clips into a single video. Pass clips as an ordered list of absolute paths (at least two); output is auto-named or written to output_path.
  • 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. Args: inpu
  • video_add_texts Overlay multiple text elements on a video in a single FFmpeg pass. Returns JSON {success, output_path}. Use when one video needs several captions at once. Pass input_path as the source video and texts as a list of overlay dicts (text plus optional position/size/color/timing). Args: input_path:
  • video_add_audio Add, replace, or mix an audio track into an existing video and render a new output file. Returns JSON {success, output_path}. Use to score or re-voice a video; source video and audio are read only. Pass video_path as the source video and audio_path as the audio file; set mix to combine or false to r
  • 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. Args: input_path: Absolute path to
  • video_convert Transcode a video into a different container or codec (mp4, webm, gif, mov, ...). Returns JSON {success, output_path}. Use for format conversion; prefer video_export for delivery presets. Pass input_path as the source video and format as the target container; long renders stream MCP progress.
  • video_speed Render a new video with playback speed changed; the source video is left unchanged. Returns JSON {success, output_path}. Use for slow-motion or fast-forward effects. Pass input_path as the source video and factor as the multiplier (below 1.0 slows, above 1.0 speeds up).
  • search_tools Find registered MCP tools by name, keyword, or a supported task phrase. Returns JSON {success, query, count, tools:[{name, description, required_params}]}. Use to find the right tool for a task without reading every description. Pass query with a term such as blur, resize, subtitle, audio, or trim,
  • video_ingest Ingest immutable source bytes into an existing or new private project.
  • video_preflight Run unified technical, loudness, color, and decode preflight.
  • video_inspect_temporal Build and persist the complete deterministic temporal evidence package.
  • video_verdict Persist exact-asset analysis; approvals require active human evidence.
  • video_acceptance_eval Evaluate exact-spec verdict and defect evidence without approving anything.
  • video_body_swap Replace video while preserving approved audio with explicit duration policy.
  • video_salvage Create one lineage-bound salvage derivative and a fresh review slot.
  • video_thumbnail Extract a single frame (thumbnail / frame grab) from a video. Args: input_path: Absolute path to the input video. timestamp: Time in seconds to extract frame. Defaults to 10% of video duration. output_path: Where to save the frame image. Auto-generated if omitted.
  • video_preview Generate a fast low-resolution preview for quick review. Args: input_path: Absolute path to the input video. output_path: Where to save the preview. Auto-generated if omitted. scale_factor: Downscale factor (4 = 1/4 resolution).
  • video_storyboard Extract key frames and create a storyboard grid for human review. Args: input_path: Absolute path to the input video. output_dir: Directory to save frames. Auto-generated if omitted. frame_count: Number of key frames to extract.
  • video_subtitles Burn subtitles (SRT/VTT/authored ASS) into a video. Args: input_path: Absolute path to the input video. subtitle_path: Absolute path to the subtitle file (.srt, .vtt, or .ass). output_path: Where to save the output. Auto-generated if omitted. style: Optional force_style override app
  • video_watermark Overlay an image watermark onto an existing video and render a new output file. The video and watermark image are read only; output_path is created or overwritten. Supports named, pixel, and percentage positions plus opacity, margin, CRF, and preset controls.
  • video_export Re-encode an existing video for final delivery using a quality preset and output format. Use this for publishing-ready renders; use video_convert when the main goal is container/codec conversion. The source video is read only and a new output file is produced.
  • video_crop Crop an existing video to a rectangular region or centered percentage crop and render a new output file. The source video is read only; x/y default to a centered crop when omitted.
  • video_rotate Rotate and/or flip an existing video and render a new output file. Supports right-angle rotations plus horizontal and vertical flips; the input video is not modified.
  • video_fade Render fade-in and/or fade-out effects onto an existing video without modifying the source file. Use fade_in for a fade from black at the start and fade_out for a fade to black at the end; output_path is created or overwritten.
  • video_edit Execute a full timeline-based edit from a JSON specification. The timeline JSON describes video clips, audio tracks, text overlays, image overlays, transitions, and export settings in a single operation. Image overlays are applied in a single filtergraph pass (no multiple re-encodes). Sequence sh
  • video_template_preview Preview what a video template would do before rendering. Analyzes the template and returns a list of operations, estimated output duration, resolution, and file size — without actually processing any video. Args: template: Template name (tiktok, youtube-shorts, instagram-reel, youtube, instagr
  • video_extract_audio Extract the audio track from a video file. Args: input_path: Absolute path to the input video. output_path: Where to save the audio file. Auto-generated if omitted. format: Audio format (mp3, aac, wav, ogg, flac).
  • video_filter Apply a visual filter to a video. Common presets: - blur: params={"radius": 5, "strength": 1} - color_preset: params={"preset": "warm"} (warm, cool, vintage, cinematic, noir) Args: input_path: Absolute path to the input video. filter_type: Filter type (blur, sharpen, brightness, co
  • video_luma_key Mask out dark regions based on luminance (brightness). Args: input_path: Absolute path to the input video. threshold: Luminance threshold (0.0-1.0). Pixels darker than this become transparent. output_path: Where to save the output. Auto-generated if omitted.
  • video_shape_mask Apply a geometric shape mask to a video. Args: input_path: Absolute path to the input video. shape: Shape to use — "circle", "rounded_rect", or "oval". output_path: Where to save the output. Auto-generated if omitted. feather: Feather radius in pixels (0 = sharp edges).
  • video_hls_segment Segment a video into HLS (HTTP Live Streaming) format. Args: input_path: Absolute path to the input video. output_dir: Directory to save segments. Auto-generated if omitted. segment_duration: Target segment duration in seconds (default 4). playlist_name: Name of the master playlist
  • video_reverse Reverse video and audio playback so it plays backwards. Args: input_path: Absolute path to the input video. output_path: Where to save the output. Auto-generated if omitted.
  • video_chroma_key Remove a solid color background (green screen / chroma key). Args: input_path: Absolute path to the input video. color: Color to make transparent in hex format (default green: 0x00FF00). similarity: How similar colors need to be to be keyed out (0.0-1.0, default 0.01). blend: How mu
  • video_normalize_audio Normalize audio loudness to a target LUFS level. Common presets: -16 (YouTube), -23 (EBU R128/broadcast), -14 (Apple/Spotify). Args: input_path: Absolute path to the input video. target_lufs: Target integrated loudness in LUFS (default -16 for YouTube). output_path: Where to save the o
  • video_overlay Picture-in-picture: overlay a video on top of another. Args: background_path: Absolute path to the background video. overlay_path: Absolute path to the overlay video. position: Position on screen. Named (top-left, etc.), pixel" " {"x": 100, "y": 50}, or percentage {"x_pct"
  • video_split_screen Place two videos side by side or top/bottom. Args: left_path: Absolute path to the first video. right_path: Absolute path to the second video. layout: Layout type (side-by-side or top-bottom). output_path: Where to save the output. Auto-generated if omitted.
  • video_detect_scenes Detect scene changes in a video. Args: input_path: Absolute path to the input video. threshold: Scene detection sensitivity (0.0-1.0, lower = more sensitive, default 0.3). min_scene_duration: Minimum scene duration in seconds (default 1.0).
  • video_create_from_images Create a video from a sequence of images. Args: images: List of absolute paths to image files (in order). output_path: Where to save the output video. Auto-generated if omitted. fps: Frames per second for the output video (default 30.0).
  • video_export_frames Export frames from a video as individual images. Args: input_path: Absolute path to the input video. output_dir: Directory for extracted frames. Auto-generated if omitted. fps: Frames per second to extract (1.0 = 1 frame per second, default 1.0). format: Output image format (jpg or
  • video_generate_subtitles Generate SRT subtitles from text entries and optionally burn into video. Args: entries: List of subtitle entries with keys: start (float), end (float), text (str). input_path: Absolute path to the input video. burn: If True, burn subtitles into the video (default False).
  • video_compare_quality Compare video quality between original and processed versions. Args: original_path: Absolute path to the original/reference video. distorted_path: Absolute path to the processed/distorted video. metrics: Metrics to compute (default: ['psnr', 'ssim']).
  • video_read_metadata Read metadata tags from a video/audio file. Args: input_path: Absolute path to the video or audio file.
  • video_write_metadata Write metadata tags to a video/audio file. Args: input_path: Absolute path to the input file. metadata: Dict of tag key-value pairs (e.g. {'title': 'My Video', 'artist': 'Me'}). output_path: Where to save the output. Auto-generated if omitted.
  • video_stabilize Stabilize a shaky video using motion vector analysis. Args: input_path: Absolute path to the input video. smoothing: Smoothing strength (default 15, higher = more stable). zooming: Zoom percentage to avoid black borders (default 0). output_path: Where to save the output. Auto-genera
  • video_apply_mask Apply an image mask to a video with edge feathering. Args: input_path: Absolute path to the input video. mask_path: Absolute path to the mask image (white = visible, black = transparent). feather: Feather/blur amount at mask edges in pixels (default 5). output_path: Where to save th
  • video_audio_waveform Extract audio waveform data (peaks and silence regions). Args: input_path: Absolute path to the input video/audio file. bins: Number of time segments to analyze (default 50).
  • video_batch Apply the same operation to multiple video files. Args: inputs: List of absolute paths to input video files. operation: Operation (trim, resize, convert, filter, blur, color_grade," " watermark, speed, fade, normalize_audio). params: Parameters for the operation. outpu
  • video_cleanup Delete intermediate video files after a workflow. Useful for multi-step pipelines that leave temporary outputs. Files in ``keep`` are preserved even if listed in ``files``. Args: files: List of absolute paths to delete. keep: List of absolute paths to preserve (optional).
  • video_composite_layers Composite ordered image/video layers from a JSON spec. Supports explicit straight/premultiplied input alpha, opacity, positioning, transforms, timing windows, masks/mattes, allowlisted blend modes, rotation, and effect-noise routes to named layer/mask/mask-edge streams. Emits a deterministic layer-
  • image_extract_colors Extract dominant colors from an image or video frame. Uses K-means clustering to find the most prominent colors. Returns hex codes, RGB values, CSS color names, and percentage coverage. Args: image_path: Absolute path to the image or video file. If video, extracts a representative frame. n
  • image_generate_palette Generate a color harmony palette from an image or video frame. Extracts the dominant color and generates harmonious colors based on color theory (complementary, analogous, triadic, split_complementary). Args: image_path: Absolute path to the image or video file. If video, extracts a representa
  • image_analyze_product Analyze a product image or video frame — extract colors and optionally generate AI description. Extracts dominant colors from an image. Optionally uses Claude Vision to generate a natural language description of the product. Args: image_path: Absolute path to the image or video file. If video,
  • still_match Match a package of stills to a hero plate with one shared WB/exposure gain. Does not overwrite sources. Writes matched stills + JSON receipt under output_dir. Per-frame auto-WB is disabled (shared gains only). Args: hero: Absolute path to the hero/establish still. inputs: Absolute paths to
  • still_grade Grade stills in order correct→match→look; optional 3D LUT applied last. Signal mode marks the LUT as signal-alignment (not film cosplay) and records near-black/near-white preservation deltas. Args: inputs: Absolute still paths. output_dir: Absolute output directory. hero: Optional hero
  • still_gate Fail-closed cohesion gate for a still package + contact sheet. Checks luma spread and shadow green/cyan wash. Returns passed=false with named metric/frame failures when the package fails. Args: inputs: Absolute still paths in the package. output_dir: Absolute directory for receipt and cont
  • image_edit Establish-locked still match with plan/receipt (intent is audit metadata). v1 pixel path is free establish mean-RGB match only; ``intent`` is required metadata and does not select pixel ops. Opted-in paid generation requests still fail because no paid still-generation adapter exists. Dry-run return
  • still_package Multi-still package workflow: edit beats → match → grade → cohesion gate. Args: establish: Absolute establish/hero still. beats: Absolute beat still paths. output_dir: Absolute package output directory. dry_run: When True, return planned graph only. apply_grade: Run ordered grad
  • video_project_create Scaffold a cinematic video project with style, storyboard, and refs folders. Args: slug: Project slug using lowercase letters, numbers, hyphens, or underscores. output_dir: Base directory for the projects/ folder. Defaults to the current working directory.
  • style_pack_read Read STYLE_ and NEG_ blocks from a style.md file or project directory. Args: path: Absolute path to style.md or to a project directory containing style.md.
  • storyboard_read Read a PUSHING CREATION storyboard table from storyboard.md or a project directory. Args: path: Absolute path to storyboard.md or to a project directory containing storyboard.md.
  • shot_prompt_render Expand one storyboard shot into prompt and negative_prompt strings. Args: project_path: Absolute path to a project directory containing style.md and storyboard.md. shot: Shot id or 1-based row number from storyboard.md.
  • hyperframes_render Render a Hyperframes composition to video. Args: project_path: Absolute path to the Hyperframes project directory. output_path: Where to save the video. Auto-generated if omitted. fps: Frame rate (24, 30, 60). width: Output width in pixels. height: Output height in pixels. q
  • hyperframes_compositions List compositions in a Hyperframes project. Args: project_path: Absolute path to the Hyperframes project directory.
  • hyperframes_preview Launch Hyperframes preview studio for live preview. Args: project_path: Absolute path to the Hyperframes project directory. port: Port for the preview server (default 3002).
  • hyperframes_still Render a single frame as image from a Hyperframes composition. Args: project_path: Absolute path to the Hyperframes project directory. output_path: Where to save the image. Auto-generated if omitted. frame: Frame number to render (default 0). variables: Inline JSON object/string wit
  • hyperframes_snapshot Capture key frames as PNG screenshots for visual verification.
  • hyperframes_inspect Inspect rendered composition layout for overflow and visual issues.
  • hyperframes_info Print Hyperframes project metadata.
  • hyperframes_catalog Browse Hyperframes catalog blocks/components.
  • hyperframes_capture Capture a website as editable Hyperframes components.
  • hyperframes_tts Generate speech audio or list available Hyperframes local TTS voices.
  • hyperframes_transcribe Transcribe audio/video to word-level timestamps or import transcripts.
  • hyperframes_remove_background Cut a person or a product out of a still or video. Default model ``u2net_human_seg`` is people-only (talking heads). For products, packaging, jewelry, bottles, ceramics, or any non-person object, pass ``model="birefnet-general"`` (requires ``pip install "kinocut[object-matte]"``). Never falls throu
  • hyperframes_doctor Run Hyperframes environment diagnostics.
  • hyperframes_benchmark Benchmark Hyperframes render speed and file size.
  • hyperframes_init Scaffold a new Hyperframes project. Args: name: Project name. output_dir: Directory to create the project in. Defaults to current directory. template: Project template (blank, warm-grain, swiss-grid). Default blank. video: Optional source video for project bootstrap. audio: Opti
  • hyperframes_add_block Install a block from the Hyperframes catalog. Args: project_path: Absolute path to the Hyperframes project directory. block_name: Registry item name (e.g. claude-code-window, shader-wipe).
  • hyperframes_validate Validate a Hyperframes project for rendering readiness. Args: project_path: Absolute path to the Hyperframes project directory.
  • hyperframes_to_mcpvideo Render a Hyperframes composition and post-process with mcp-video in one step. Args: project_path: Absolute path to the Hyperframes project directory. post_process: List of post-processing operations, each with 'op' and 'params' keys. Example: [{"op": "resize", "params": {"aspect_rat
  • video_record_motion_acceptance Record an authorized human caller's explicit whole-film motion attestation. The caller must provide the exact source/report hashes, complete watched intervals and every flagged interval's disposition. Requires explicit human review; agents must not invent viewing or act as the reviewer. This record
  • video_mix_audio Mix timed sounds with one AAC encode and stream-copy the primary picture. Sounds is an array or JSON array of objects with path, start (seconds), volume (linear gain), fade_in and fade_out (seconds). The picture duration and relative source-audio timing are preserved. Tracks sum without loudness no
  • audio_synthesize Generate audio procedurally using synthesis. Creates WAV files from scratch using mathematical waveforms. No external audio files needed. Supports envelopes, reverb, filtering, and fade effects. Args: output_path: Absolute path for the output WAV file. waveform: Waveform type (sine, square
  • audio_preset Generate preset sound design elements. Pre-configured sound effects for common use cases. No external audio files needed. Available presets: - UI: ui-blip, ui-click, ui-tap, ui-whoosh-up, ui-whoosh-down - Ambient: drone-low, drone-mid, drone-tech - Notifications: chime-success, chime-error, chime-
  • audio_sequence Compose multiple audio events into a timed sequence. Creates a layered audio track from multiple timed sound events. Args: sequence: List of audio events, each with: - type: "tone", "preset", or "whoosh" - at: Start time in seconds - duration: Event duration in seconds
  • audio_compose Layer multiple audio tracks with volume mixing. Mix multiple WAV files together with individual volume control. Args: tracks: List of track configs with: - file: Absolute path to WAV file - volume: Volume multiplier 0-1 - start: Start time offset in seconds - lo
  • audio_effects Apply audio effects chain to a WAV file. Process audio through a chain of effects like reverb, filtering, normalization. Args: input_path: Absolute path to input WAV file. output_path: Absolute path for output WAV file. effects: List of effect configs with: - type: "lowpass", "
  • video_add_generated_audio Add procedurally generated audio to a video. One-shot convenience function to generate and add audio to video. Args: input_path: Absolute path to input video. audio_config: Configuration dict with: - drone: {"frequency", "volume"} for background tone - events: List of timed
  • video_audio_spatial Apply 3D spatial audio positioning.
  • video_duck_audio Mix background music under a video's voice with automatic ducking. The video's own audio (voice/dialog) drives FFmpeg's sidechain compressor, so the music dips while speech plays and recovers in pauses — the standard treatment for shorts, reels, and podcast clips. Args: input_path: Video whose
  • video_audio_bed Mix a looped music bed under a voice source with ducking and loudness normalization. The voice drives sidechain ducking and loudness normalization. A deterministic AudioBedReceipt is returned, and output duration stays locked to the voice source. Args: voice_source: Video/audio whose existing
  • effect_vignette Apply vignette effect - darkened edges. Creates a darkened border effect that draws attention to the center of the frame. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. intensity: Darkness amount 0-1. Default 0.5. radius: Vignette radiu
  • effect_chromatic_aberration Apply chromatic aberration - RGB channel separation. Creates a trendy RGB split effect popular in tech/glitch aesthetics. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. intensity: Pixel offset amount. Default 2.0. angle: Separation dire
  • effect_scanlines Apply CRT-style scanlines overlay. Simulates old CRT monitor scanline effect with optional flicker. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. line_height: Pixels per scanline. Default 2. opacity: Line opacity 0-1. Default 0.3.
  • effect_noise Apply film grain or digital noise. Adds texture noise to video for vintage or lo-fi aesthetics. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. intensity: Noise amount 0-1. Default 0.05. mode: Noise type (film, digital, color). Default f
  • effect_glow Apply bloom/glow effect for highlights. Creates a soft glow around bright areas of the video. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. intensity: Glow strength 0-1. Default 0.5. radius: Blur radius in pixels. Default 10. thres
  • video_layout_grid Create grid-based multi-video layout. Arranges multiple videos in a grid pattern (2x2, 3x1, etc.). Args: clips: List of absolute paths to video files. layout: Grid layout (2x2, 3x1, 1x3, 2x3). output_path: Absolute path for output video. gap: Pixels between clips. Default 10. p
  • video_layout_pip Picture-in-picture overlay. Overlay a smaller video on top of a main video. Args: main_path: Absolute path to main video. pip_path: Absolute path to picture-in-picture video. output_path: Absolute path for output video. position: Position (top-left, top-right, bottom-left, bottom-r
  • video_text_animated Add animated text to video. Overlay text with animation effects (fade, slide, etc.). Args: input_path: Absolute path to input video. text: Text to display. output_path: Absolute path for output video. animation: Animation type (fade, slide-up, typewriter). Default fade. font: F
  • video_subtitles_styled Burn subtitles from SRT/VTT with custom styling. Embeds subtitle file into video with customizable appearance. Args: input_path: Absolute path to input video. subtitles_path: Absolute path to SRT or VTT file. output_path: Absolute path for output video. style: Optional style dict w
  • video_mograph_count Generate animated number counter video. Creates a standalone video of an animated counting number. Args: start: Starting number. end: Ending number. duration: Animation duration in seconds. output_path: Absolute path for output video. style: Optional style dict with font, size,
  • video_mograph_progress Generate progress bar / loading animation. Creates a standalone progress animation video. Args: duration: Animation duration in seconds. output_path: Absolute path for output video. style: Progress style (bar, circle, dots). Default bar. color: Progress color hex. Default #CCFF00.
  • video_info_detailed Get extended video metadata. Returns detailed video information including scene change detection and dominant colors. Args: input_path: Absolute path to input video. Returns: Dict with duration, fps, resolution, bitrate, has_audio, scene_changes.
  • video_auto_chapters Auto-detect scene changes and create chapters. Analyzes video for scene cuts and returns chapter timestamps. Args: input_path: Absolute path to input video. threshold: Scene detection threshold 0-1. Default 0.3. Returns: List of (timestamp, description) chapter tuples.
  • transition_glitch Apply glitch transition between two video clips. Args: clip1_path: Absolute path to first video clip. clip2_path: Absolute path to second video clip. output_path: Absolute path for output video. duration: Transition duration in seconds (default 0.5). intensity: Glitch intensity
  • transition_pixelate Apply pixelate transition between two video clips.
  • transition_morph Apply morph transition between two video clips.
  • glitch_rgb_shift Apply RGB channel shift glitch effect. Shifts red and blue channels in opposite directions for a chromatic split look. Optionally adds per-frame noise for a jittery feel. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. amount: Shift distance
  • glitch_scanline_jitter Apply scanline jitter glitch effect. Displaces random horizontal rows of pixels for a CRT malfunction look. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. jitter_amount: Max horizontal displacement in pixels. Default 15. frequency: Frac
  • glitch_screen_tearing Apply screen tearing glitch effect. Creates horizontal tear bands at varying Y positions that shift left/right over time. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. tear_count: Number of tear bands. Default 5. offset_range: Max hori
  • glitch_vhs_tracking Apply VHS tracking error glitch effect. Simulates VHS tape tracking problems with color bleed, rolling bands, and analog noise. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. tracking: Tracking error intensity (0-1). Default 0.5. noise_
  • glitch_macroblocking Apply macroblocking glitch effect. Simulates codec artifacting by downscaling/upscaling to create blocky pixelation combined with color posterization. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. block_size: Block size in pixels. Default
  • glitch_datamoshing Apply datamoshing glitch effect. Simulates P-frame corruption where displacement drifts across frames then periodically resets, mimicking real datamosh artifacts. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. drift: Max displacement drift
  • glitch_cmyk_split Apply CMYK split glitch effect. Shifts RGB channels at 90-degree intervals to simulate four-plate offset print registration errors. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. amount: Shift distance in pixels. Default 8. angle: Base
  • glitch_turbulent_displacement Apply turbulent displacement glitch effect. Uses layered sin/cos expressions at different frequencies to approximate fractal Brownian motion noise for organic-looking displacement. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. amount: Disp
  • glitch_digital_feedback Apply digital feedback glitch effect (requires Node.js + GPU). Iterative frame feedback with scale/rotation transform. Each frame blends with a scaled+rotated version of the previous output, creating ghostly trails and recursive visual patterns. Args: input_path: Absolute path to input video.
  • glitch_slit_scan Apply slit-scan temporal displacement effect (requires Node.js + GPU). Each row/column of the output is sampled from a different past frame, creating a time-smeared effect reminiscent of slit-scan photography. Args: input_path: Absolute path to input video. output_path: Absolute path for o
  • glitch_depth_splatting Apply depth-based point splatting effect (requires Node.js + GPU). Extracts pseudo-depth from luminance and renders the image as scattered points, creating a 3D particle-like appearance. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. depth_
  • glitch_point_cloud Apply point cloud rendering effect (requires Node.js + GPU). Samples the image as scattered points arranged in a 3D-rotated grid, with depth-based displacement creating a volumetric look. Args: input_path: Absolute path to input video. output_path: Absolute path for output video. densi
  • video_ai_remove_silence Remove silent sections from video.
  • video_ai_transcribe Transcribe speech to text using Whisper.
  • video_analyze Comprehensive video analysis — transcript, metadata, scenes, audio, quality, chapters, colors. Accepts a local file path or an HTTP/HTTPS URL. Direct video URLs (e.g. https://example.com/clip.mp4) are downloaded automatically. Streaming-platform URLs (YouTube, Vimeo, TikTok, Twitter/X, Instagram, T
  • video_ai_scene_detect Detect scene changes in video.
  • video_ai_stem_separation Separate audio into stems using Demucs.
  • video_ai_upscale Upscale video using AI super-resolution.
  • video_ai_color_grade Apply a color grade to a video — by LUT file, style preset, or reference video. Args: input_path: Video file to grade. output_path: Where to write the graded video. reference_path: Optional reference video — when given, the video's color balance is adjusted to match the referenc
  • video_quality_check Run visual quality checks on a video. Analyzes brightness, contrast, saturation, audio levels, and color balance. Returns quality scores and recommendations. Args: input_path: Absolute path to video file fail_on_warning: If True, treat warnings as failures
  • video_release_checkpoint Create preview artifacts only after the video passes quality gates. Use this before publishing or chaining more polish effects. It runs a hard quality gate, then writes a thumbnail and storyboard for human inspection. A video with no audio stream fails the gate unless ``require_audio`` is explicitl
  • video_design_quality_check Run comprehensive design quality analysis on a video. Checks layout, typography, color, motion, and composition quality. Can automatically fix issues where possible. Args: input_path: Absolute path to video file auto_fix: If True, automatically apply fixes strict: If True, treat warnin
  • video_fix_design_issues Auto-fix design issues in a video. Applies automatic fixes for brightness, contrast, saturation, and audio level issues. Args: input_path: Absolute path to input video output_path: Absolute path for output (auto-generated if omitted)
  • video_find_moments Persist or query a revision-bound local semantic index.
  • video_project_recipe_export Export a verified edit revision as a path-free portable recipe.
  • video_project_recipe_replay Replay a portable recipe into a new durable project revision.
  • video_intent Route a semantic intent verb to a plan (does not silently mutate media). Optional ``goal`` compiles a reviewable cutfile (N1) without rendering.
  • video_propose_broll Transcript-keyed b-roll proposals — human review required, never silent insert.
  • video_translate_captions Translate SRT captions with honest language-coverage reporting (EN→ES first).
  • video_language_coverage Honest per-surface language coverage for transcribe/translate/dub.
  • video_review_run Watching guardrail: run offline metric floor under a review policy.
  • video_review_decide Record human accept/reject/revise. Accept + EDL approval can render (N4).
  • video_propose_mutations Map QC findings to typed proposed mutations (human apply only).
  • video_init_project Scaffold a local Kinocut project directory (media/out/receipts + optional Cutfile).
  • video_brand_kit Save or load a brand kit / style profile JSON.
  • video_estimate_operation Dry-run local wall-time / cost-unit estimate (not cloud pricing).
  • video_cutfile_validate Validate a Cutfile, or compile one from ``goal`` / ``platform`` (N1/N5).
  • video_cutfile_render Render a schema-valid Cutfile via the workflow engine (Track E).
  • video_metric_qc Offline metric floor (duration/black/loudness) — fail-closed, no invented values.
  • video_timeline_ir_validate Validate Timeline IR and compile to render DAG (P3.0). Semantic timelines (shots/silences/words) also get agent-visible ``text`` (N2).
  • video_qc_vision Prepare keyframes for visual review; semantic vision QC is not evaluated. Returns retained frame paths, sampling_status and assessment_status. Frame preparation is not a visual-quality pass. No executable VLM is available; require_vlm=True returns verdict=fail and blocked=True.
  • video_qc_narrative Narrative/retention heuristics incl. first-15s window (P3.4).
  • video_generative_plan Generative policy and spend-cap planning metadata (P4.1). Eligibility never proves execution: this tree has no generation adapter.
  • video_otio_export Export Timeline IR to simplified OTIO JSON (P4.2).
  • video_otio_import Import simplified OTIO JSON to Timeline IR (P4.2).
  • video_review_ui Write hot-reloading human review HTML surface (P4.3).
  • video_dub_plan ES-first plan; use sound_voice_batch with a hashed request for local stock speech.
  • video_publish_validate Validate a publish spec. ``solve=True`` also emits a cutfile (N5).
  • video_hook_candidates Thumbnail + hook-title candidates for human pick (TE.2).
  • video_audiogram_plan Audiogram + chapter mark plan (TE.4).
  • video_punch_zoom_plan Auto-zoom punch-in plan on cut points (TE.5).
  • video_seek_frame Frame-accurate seek conversion (TE.9).
  • video_edit_session Conversational edit session. Step with ``input_path`` measures real QC (N6).
  • shorts_plan_show Load a saved shorts plan and return source-free proposals for review.
  • shorts_review Append one human review decision to a saved shorts plan (source-free).
  • shorts_render Render platform drafts for an approved candidate from a saved plan.
  • shorts_package Package approved platform renders from a saved plan. Never posts.
  • sound_capabilities Discover the bounded public sound operation set (local-first, JSON-safe).
  • sound_plan_validate Validate a SoundPlan payload (or a built-in minimal plan when omitted).
  • sound_voice_batch Retain local caption speech from a request, or run the synthetic plan demo.
  • sound_mix_render Assemble supplied WAVs into a new ZIP; omit both arguments for a labelled demo.
  • sound_master_render Retain a two-pass master only after measuring final audio against its policy.
  • sound_qa_loudness Measure hashed local audio against its policy; omit inputs for a labelled demo.
  • sound_qa_asr Recognize supplied local audio and compare it with a reference script.
  • video_repurpose_plan Create a dry-run local repurposing manifest for platform-ready assets.
  • video_repurpose Submit one durable projectstore repurpose job for platform clips. The worker applies the requested release checkpoint policy before success. Submission acknowledges queued/running work, not quality or human acceptance.
  • video_validate_text_layout Validate a set of text overlays for visual failure modes before rendering. Checks for: text overlap, low contrast, unsafe positioning, excessive sequential overlays, and missing shadows. Args: overlays: List of overlay specs with keys: text, position, size, color, shadow (optiona
  • video_extract_frame Extract a frame using the same sampling as CLI and Python frame extraction. Omitted timestamps use smart thumbnail selection when available, falling back to 10% of the clip duration. Pass 0 explicitly to extract the first frame. Args: input_path: Absolute path to the video. timestamp: Expl
  • video_workflow_validate Validate an agent workflow job-spec without rendering any media. Runs the fail-closed structural validator over the JSON job-spec at ``spec_path``: op allowlist (probe|trim|resize|convert|merge|add_text|composite_layers), symbolic ``@ref`` resolution (@sources.<id>, @work/<name>, @outputs.<id>), ba
  • video_workflow_plan Produce a no-render plan for an agent workflow job-spec. Validates the spec first (fail-closed) and then builds a dry-run plan artifact WITHOUT rendering any media: the ordered operation graph, per-source ffprobe results (duration/resolution/codec) and sha256 content hashes where the source file ex
  • video_workflow_render Execute an agent workflow job-spec and return a provenance receipt. Validates the spec first (fail-closed), then runs each allowlisted op (probe|trim|resize|convert|merge|add_text|composite_layers) SEQUENTIALLY in spec order via the backing engine functions. Intermediates are written to a per-run `
  • video_workflow_inspect Summarize any receipt this project emits, with a read-only integrity check. Reads a workflow render receipt, a dry-run ``workflow_plan`` artifact, or a ``layer_plan`` receipt (v1 legacy with NO ``receipt_kind`` field, or v2) at ``receipt_path`` and returns a NORMALIZED inspection: the kind (inferre
  • video_rescue_plan Analyze one local video and return a policy-classified rescue plan. Planning never changes the source or renders final media. It records findings, safe repair ids, recommendations, unavailable and blocked work, local capability evidence, previews, and an execution estimate.
  • video_rescue_render Render approved safe repairs from a reviewed rescue plan. Approval ids must name safe repairs in this exact immutable plan. The renderer fails closed on stale inputs, capabilities, policy, resume state, cancellation, or verification failure and never promotes failed output.
  • video_rescue_inspect Inspect a rescue plan or receipt and re-check artifact integrity.
  • video_semantic_timeline Build a local, source-time semantic timeline from supplied analyzer evidence.
  • video_semantic_query Query source-backed semantic spans locally without inventing descriptions.
  • video_timeline_edit_plan Plan explicit or ordinary-person timeline edits as a reviewable EDL and diff.
  • video_visual_transform_plan Plan subject/camera analysis, reframing, or stabilization with crop budgets.
  • video_restoration_plan Plan or evaluate evidence-gated local restorative work.
  • video_composition_plan Build source-backed manifests, selections, compositions, previews, and checks.
  • video_creative_autopilot_plan Coordinate proven local planners or return a structured abstention.
  • video_remote_egress_plan Plan explicit remote egress and fake adapter receipts without network I/O.
  • video_review_package Assemble a review package and publish-gate verdict for a candidate artifact.
  • video_publish_gate Evaluate the fail-closed publish gate; any blocking finding blocks publishing.
  • video_review_decision Record a human review decision (writer); corrections supersede by record id.
  • video_learning_report Project a learning report (verdicts, defects, costs, recipes) from records.
  • video_cost_ledger Sum known USD cost events by category for the project.
  • video_recipe_capture Capture a workflow recipe (writer); idempotent by canonical digest.
  • video_capabilities Probe host capabilities (ffmpeg, whisper, c2pa) and return a capability report.
  • video_benchmark_run Run the AI-video benchmark corpus against host capabilities.
  • revideo_materialize Materialize Kinocut's pinned Revideo project for a validated job.

Badge

Connect-MCP badge for tech.kyanitelabs/kinocut

Markdown for your README
[![Connect-MCP](https://clawy.uk/mcp/badge/tech.kyanitelabs/kinocut.svg)](https://clawy.uk/mcp/s/tech.kyanitelabs/kinocut)

Repository · Website