Blender integration through the Model Context Protocol
unflick is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Control the unflick video player: play files/URLs, search transcripts, cut clips, 114 MCP tools.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user unflick-mcp '--' npx -y unflick-mcp
# 2 — ask your agent for something these tools do
# dev_snapshot, dev_click, dev_text and 111 more
unflick costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts unflick as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user unflick-mcp '--' npx -y unflick-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
114 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
The accessibility tree of the unflick window: every visible element with its role, accessible name, state and a CSS selector that feeds straight back into dev_click and dev_text. Reach for this first — it is how you find out what is on screen. Invisible nodes and unnamed wrappers are elided, so…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | no | Scope to a subtree instead of the whole document. |
| depth | integer | no | How deep to descend. Default 12. |
Click an element in the unflick window. Polls for the selector first, so a click issued right after an action does not race the render, then hit-tests the point before dispatching: if something else is on top, the click is refused and the covering element is named rather than reported as a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | CSS selector. Take it from dev_snapshot. |
| index | integer | no | Which match, 0-based, when the selector is ambiguous. |
| timeout_seconds | number | no | How long to wait for the selector to appear. Default 5. |
Visible text of every element matching a selector, each with its index. Several matches are returned rather than refused — reading is not acting. Use it to check what a list, a menu or a label actually says, which is where 'undefined' shows up.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | CSS selector. |
Wait for an element to appear, or with gone for it to leave the page. The second half is not optional: verifying that a panel closed is impossible without it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| selector | string | yes | CSS selector. |
| gone | boolean | no | Wait for it to disappear instead of appear. |
| timeout_seconds | number | no | How long to wait. Default 10. |
A picture of the unflick interface. This is the UI layer, not the decoded video: mpv draws on its own surface, which sits above the webview on Windows and below it on macOS and Linux, so no single grab means the same thing on all three. Use describe_frame for the picture itself — it comes from…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| max_edge | integer | no | Longest edge of the returned image in pixels. Default 768. |
Run JavaScript in the unflick window and get back what it evaluated to. Either an expression or statements with an explicit return. The escape hatch for what the other five verbs do not cover — prefer them where they fit, because they report their own refusals in terms of the page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| script | string | yes | JavaScript to run. |
| timeout_seconds | number | no | How long to wait for an answer. Default 5. |
Get or set the shape of the player window the user is looking at. normal is the full player, pip is a small always-on-top video window, music is the compact audio layout with cover art and tags. Call with no arguments to read the current mode. Only works while the unflick GUI is running —…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | Mode to switch to. Omit to read the current one. |
Find files an older unflick left behind — on Windows, upgrading from v0.9 moved the install directory and stranded roughly half a gigabyte with no uninstall entry. Reports by default; pass apply to delete. The live thumbnail and cover caches share that folder and are never touched.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| apply | boolean | no | Delete what was found. Omit to report only. |
Send what is playing to a television on the network over DLNA. "list" finds renderers; "to" starts a cast (naming a renderer, or omitting it when there is only one) and pauses playback here so it is not heard twice; "stop", "pause", "resume", "seek" and "status" drive it once it is running. Only…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | Defaults to status. |
| renderer | string | no | Which renderer, by name or part of it. Omit when there is only one. |
| file | string | no | A file to cast instead of what is playing. |
| seconds | number | no | For seek, where to go. For list and to, how long to wait for renderers to answer (default 3). |
Optical drives on this machine and whether each holds a DVD or Blu-ray, plus whether this build can play them at all. Play one with play and the drive path ("D:\\"), a disc image ("film.iso"), or a folder holding VIDEO_TS / BDMV; a specific title is mpv's own syntax, "dvd://3". Each drive, and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | Ask about one path instead of listing drives — reports what it is without opening it. |
What the user was last watching and how far in — and, with action "restore", reopen it there. unflick writes this down every few seconds while playing, so it survives a closed window or a crash. Use it when someone asks to get back to what they were watching without naming the file. "clear"…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | Defaults to show, which only reports. |
The last launch's startup timeline, phase by phase, in milliseconds from process start — process init, video pipeline, window shown, the launch file opening, React mounting, the control port. Use it to say where a slow start went rather than that it was slow.
No parameter schema on file.
What is playing, described the way a person would: title, artist, album, and whether there is any picture (an embedded cover is not video). Use this rather than get_status when the question is 'what is this', and get_status when it is 'where are we'.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cover | boolean | no | Also extract the embedded cover art and return its path on disk. Costs one ffmpeg run the first time per file. |
Read the 10-band equaliser: per-band gains in dB, the band centre frequencies they correspond to, the preamp, whether loudness normalisation is on, and the filter chain mpv is actually running. Read this before changing a band so you adjust the user's curve instead of replacing it.
No parameter schema on file.
Adjust the equaliser. Set one band with band (0-9, low to high) plus gain in dB, or the whole curve at once with bands. enabled switches the equaliser in and out without discarding the curve, normalize evens out quiet dialogue against loud action, and preamp makes headroom so boosted…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| band | integer | no | Band index 0-9: 31, 62, 125, 250, 500, 1000, 2000, 4000, 8000, 16000 Hz |
| gain | number | no | Gain in dB for that band, -12 to 12 |
| bands | array | no | All ten gains in dB, low frequency first |
| enabled | boolean | no | Switch the equaliser on or off, keeping the curve |
| normalize | boolean | no | Dynamic loudness normalisation |
| preamp | number | no | Preamp in dB, -20 to 12 |
Apply a named equaliser curve and switch the equaliser on. Use equalizer_presets to see what exists and what each is for. 'speech' lifts dialogue out of a loud mix and 'night' tames explosions while keeping voices — those two answer most requests about not being able to hear what people are saying.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Preset name, e.g. speech, night, bass, treble, headphones, flat |
List the available equaliser presets with a description of what each is for and the curve it applies.
No parameter schema on file.
Remove every audio filter: flat curve, no preamp, no normalisation.
No parameter schema on file.
Read or set whether changing playback speed keeps the original pitch. On by default, which is what makes 1.5x speech listenable rather than chipmunk-like. Turn it off only when the pitch shift is the point, such as checking a musical tempo change.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| enabled | boolean | no | Omit to read the current setting |
Play a video file or URL. URLs from supported streaming sites (YouTube, Bilibili, Twitch, Vimeo, etc.) are extracted via the bundled yt-dlp before playback.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | Path to a local video file, or HTTP(S) URL to a streaming site. |
| seek | number | no | Seek to position in seconds |
| volume | integer | no | Volume level (0-100) |
| speed | number | no | Playback speed multiplier |
| proxy | string | no | Optional proxy URL forwarded to yt-dlp for URL extraction (e.g. http://127.0.0.1:7890) |
Pause playback. Acts on the player the user is watching — when the unflick window is open, this pauses the video on screen.
No parameter schema on file.
Resume playback after a pause. From end-of-file this rewinds to the start rather than doing nothing.
No parameter schema on file.
Stop playback and unload the file. The resume point is saved unless the file was watched to the end.
No parameter schema on file.
Seek to a position in seconds
| Parameter | Type | Required | Notes |
|---|---|---|---|
| seconds | number | yes | Position in seconds |
Set volume level
| Parameter | Type | Required | Notes |
|---|---|---|---|
| level | integer | yes | Volume level (0-100) |
Get or set the playback speed of the window the user is watching. Call with no arguments to read the current rate. Pitch is corrected by default, so speech stays natural — see the pitch CLI command to turn that off.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| rate | number | no | Speed multiplier between 0.01 and 100 (e.g. 1.5). Omit to read the current rate. |
| relative | boolean | no | Treat rate as an offset from the current speed instead of an absolute multiplier. Clamped to the valid range. |
Get current playback status including state, file, position, duration, volume, and speed. file is the path the user gave; key is what resume points and bookmarks are filed under (the same string, except for a mounted disc, where it identifies the disc rather than the drive) and label is a…
No parameter schema on file.
Get media file metadata (duration, resolution, codecs) without affecting current playback
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | Path to the media file |
Add a file to the playlist
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | Path to the media file |
Remove a playlist entry by index
| Parameter | Type | Required | Notes |
|---|---|---|---|
| index | integer | yes | Index of the entry to remove |
List all playlist entries with index, path, and current track indicator
No parameter schema on file.
Advance to and play the next track in the playlist
No parameter schema on file.
Go back to and play the previous track in the playlist
No parameter schema on file.
Clear all entries from the playlist
No parameter schema on file.
Play a specific playlist entry by index
| Parameter | Type | Required | Notes |
|---|---|---|---|
| index | integer | yes | Index of the playlist entry to play |
Load an external subtitle file
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | yes | Path to the subtitle file (.srt, .ass, .sub) |
List all subtitle tracks (embedded and external)
No parameter schema on file.
Select a subtitle track by ID (0 to disable subtitles). Choosing a single track turns bilingual mode off.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Subtitle track ID (0 to disable) |
List all audio tracks (embedded)
No parameter schema on file.
Select an audio track by ID (0 to disable audio)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Audio track ID (0 to disable) |
Generate subtitles for a video using whisper. Mode 'local' uses bundled or supplied whisper.cpp; mode 'api' uses OpenAI. Returns the path of the generated .srt file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| video | string | yes | Path to the video file |
| mode | string | no | Transcription mode (auto-detected from arguments if omitted) |
| whisper | string | no | Path to whisper-cli (local mode; auto-detects bundled if omitted) |
| model | string | no | Path to whisper model (local mode; auto-detects bundled if omitted) |
| api_key | string | no | OpenAI API key (api mode) |
| output_dir | string | no | Output directory for the .srt file |
Translate an SRT file to another language using OpenAI. Returns the path of the translated .srt file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| srt | string | yes | Path to the source .srt file |
| target_lang | string | yes | Target language (e.g. 'Chinese', 'Spanish') |
| api_key | string | yes | OpenAI API key |
| output_dir | string | no | Output directory |
Scan a directory for video files and add them to the library
| Parameter | Type | Required | Notes |
|---|---|---|---|
| dir | string | yes | Directory path to scan |
Search the media library by title or path
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Search query |
List all media files in the library
No parameter schema on file.
Remove a media entry from the library by ID
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Media entry ID to remove |
Extract a video clip segment, optionally as GIF. Requires ffmpeg in PATH.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | no | Input file path (uses currently playing file if omitted) |
| start | number | yes | Start time in seconds |
| end | number | yes | End time in seconds |
| output | string | no | Output file path (auto-generated if omitted) |
| gif | boolean | no | Export as GIF instead of MP4 |
Take a screenshot of the current video frame
| Parameter | Type | Required | Notes |
|---|---|---|---|
| output | string | no | Output file path (optional, auto-generated if omitted) |
Save playback position for a file (for resume playback)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path to the media file |
| position | number | yes | Position in seconds |
Get saved playback position for a file
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path to the media file |
Get the absolute path of the settings.json file
No parameter schema on file.
Read all settings, or a single key if provided
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | no | Optional key name; omit to read all settings |
Set a single settings key to the given JSON value
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | Key name |
| value | yes | Any JSON value (string, number, bool, object, array) |
Remove a single settings key
| Parameter | Type | Required | Notes |
|---|---|---|---|
| key | string | yes | Key name to remove |
List current video filter values (brightness, contrast, saturation, gamma, hue)
No parameter schema on file.
Set a video filter (brightness | contrast | saturation | gamma | hue) to a value in -100..100
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| value | integer | yes | — |
Reset all video filters to 0 (neutral)
No parameter schema on file.
Fetch SponsorBlock skip segments for a YouTube URL. Returns the configured categories plus a list of {start, end, category, action_type, uuid} segments. Empty list when none exist (404). Errors only on network/parse failure or non-YouTube URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | YouTube URL (watch / shorts / youtu.be / embed) |
Get or set the subtitle delay in seconds. Positive values show subtitles later. Call with no arguments to read the current delay. Useful for correcting AI-generated subtitles, which often drift a few hundred milliseconds from the dialogue.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| seconds | number | no | Delay in seconds. Omit to read the current value. |
| relative | boolean | no | Treat seconds as an offset from the current delay instead of an absolute value |
Get or set the audio delay in seconds, for fixing lip-sync. Positive values play audio later. Call with no arguments to read the current delay.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| seconds | number | no | Delay in seconds. Omit to read the current value. |
| relative | boolean | no | Treat seconds as an offset from the current delay instead of an absolute value |
Read subtitle appearance: scale, vertical position, colour, border size, bold.
No parameter schema on file.
Set one subtitle appearance property. Returns the full style after the change.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| value | yes | scale: 0.1-10 · pos: 0-150 (100 = bottom) · color: #RRGGBBAA · border_size: 0-20 · bold: boolean |
Show two subtitle tracks at once — typically the original plus a translation. Call with no arguments to read the current state. primary is the bottom line and the one subtitle_select refers to; secondary is drawn just above it. Each accepts a track id from subtitle_list or a path to a…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| enabled | boolean | no | Turn it on or off. Omit to read; omitting it while naming a track or layout turns it on. |
| primary | string/integer | no | Bottom line: a track id, or a path to a subtitle file |
| secondary | string/integer | no | The line above it: a track id, or a path to a subtitle file |
| layout | string | no | stacked (just above the first line, the default) or top of the frame |
List the chapters of the currently playing file: index, title, start time, and which one is playing. Returns an empty list for files without chapters.
No parameter schema on file.
Jump to a chapter by 0-based index.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| index | integer | yes | 0-based chapter index |
Jump to the next chapter. Clamps at the last chapter.
No parameter schema on file.
Jump to the previous chapter. Clamps at the first chapter.
No parameter schema on file.
Control the A-B loop, which repeats a section of the current file. Set point A and point B to start looping; clear to stop. Omit position to use the current playback position.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | a/b set a loop bound, clear removes both, status reads them |
| position | number | no | Position in seconds for the a/b actions. Defaults to the current position. |
Step forward exactly one frame. Pauses playback, as frame stepping is for inspecting a still.
No parameter schema on file.
Step back exactly one frame. Pauses playback.
No parameter schema on file.
Get or set the playlist repeat mode. 'off' stops after the last entry, 'one' loops the current file, 'all' wraps around. Call with no arguments to read the current mode.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| mode | string | no | — |
Get or set playlist shuffle. Enabling it reorders playback without renumbering entries, and keeps the current track playing. Call with no arguments to read the current setting.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| enabled | boolean | no | — |
Shut down the unflick daemon. Declined when the control port is held by the GUI — close the window instead.
No parameter schema on file.
Find and load subtitles for the playing video from OpenSubtitles, in one step. Picks the best match: a subtitle synced against this exact file if one exists (checked by file hash, so the timing is correct), otherwise the most-downloaded subtitle for the title. Prefer this over generate_subtitles…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Search text. Omit to derive a title from the playing file's name. |
| file | string | no | Video to match against. Defaults to the playing file. |
| languages | string | no | Comma-separated OpenSubtitles language codes, e.g. "zh-CN,en". Defaults to the opensubtitles_languages setting, else English. |
| load | boolean | no | Load the subtitle into the player after downloading (default true) |
Search OpenSubtitles and return the candidates without downloading anything. Use this when the user should choose, or to check what exists before spending a download. Each result carries a file_id for download_subtitle, plus moviehash_match — true means it is synced to this exact file. Costs no…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Search text. Omit to derive a title from the playing file's name. |
| file | string | no | Video to match against. Defaults to the playing file. |
| languages | string | no | Comma-separated OpenSubtitles language codes, e.g. "zh-CN,en" |
| hash | boolean | no | Match by file hash as well as title (default true). Set false to search by title only. |
Download one subtitle chosen from find_subtitles and load it into the player. Saved next to the video when that directory is writable, so it loads automatically next time. Costs one of the user's limited daily OpenSubtitles downloads.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file_id | integer | yes | The file_id from a find_subtitles result |
| file | string | no | Video to save the subtitle beside. Defaults to the playing file. |
| language | string | no | Language code of the chosen subtitle, used in the saved filename |
| load | boolean | no | Load it into the player after downloading (default true) |
Search the currently playing file's subtitles for a phrase and return every match with its timestamp and speaker (if known). Works with loaded subtitle files, sidecar .srt/.vtt/.ass/.ssa files, embedded text tracks, and subtitles you generated with generate_subtitles. Use this to answer questions…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Phrase to look for |
| limit | integer | no | Maximum matches to return (default 20, max 200) |
| speaker | string | no | Optional speaker filter (case-insensitive substring match) |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Jump playback to where a phrase is spoken. Finds the phrase in the subtitles (optionally filtered by speaker) and seeks just before that line, so the sentence is heard from its start. This is the 'skip to the part where they talk about X' tool.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Phrase to jump to |
| occurrence | integer | no | Which occurrence, 1-based (default 1) |
| speaker | string | no | Optional speaker filter |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Return the full transcript of the currently playing file as timed cues (including speaker labels when present), plus where it came from. Use it to read or summarise a video, or as input for writing your own chapter list with set_chapters. Long videos produce a lot of text — prefer…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| speaker | string | no | Optional speaker filter (case-insensitive) |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Return a compact, structured overview of a video's transcript: cue count, word count, speaking duration, top keywords, and timeline segments with representative lead lines. Much smaller than transcript_get on a long video, so reach for this first when asked what a video is about or how it is…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| segments | integer | no | Number of timeline segments to divide the transcript into (1-20, default 5) |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Search spoken dialogue across every video in the media library that has a sidecar (.srt/.vtt) or cached transcript. Returns each matching cue with its video path, title, and timestamp so you can immediately open that video at that line with play (passing file and seek).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Phrase to search for across the library (case-insensitive) |
| limit | integer | no | Maximum matches to return (1-200, default 20) |
Give a file that has no chapters a set of them, derived from the pauses in its transcript. The result becomes real navigation: it shows up in chapter_list, marks the progress bar, and responds to chapter_seek. This is a rough heuristic — if you have read the transcript, set_chapters will give…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| count | integer | no | Roughly how many chapters to aim for (2-50, default 8) |
Set the chapter list for a file that has none, from your own reading of its content. Times are in seconds; they are sorted and clamped to the file automatically. These become real chapters — navigable with chapter_seek and drawn on the progress bar. Fails if the file already ships with its own…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| chapters | array | yes | Chapter marks in playback order |
Remove chapters added by generate_chapters or set_chapters. A file's own built-in chapters are not affected.
No parameter schema on file.
List every keyboard shortcut: action id, label, current key, default, and whether the user has changed it. Keys read as Mod+Alt+Shift+key, where Mod is Ctrl on Windows/Linux and Cmd on macOS.
No parameter schema on file.
Rebind a keyboard shortcut. Fails if the key is already taken by another action, naming the conflict rather than silently stealing it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | yes | Action id from keybind_list, e.g. play_pause |
| key | string | yes | Key, e.g. k · Shift+z · Mod+o · PageUp |
Restore a shortcut to its default. Omit action to reset every binding at once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | Action id. Omit to reset all. |
Read how the picture is fitted to the window: aspect override, rotation, zoom multiplier, pan-scan and deinterlace. Distinct from filter_list, which is colour rather than geometry.
No parameter schema on file.
Fix a squashed aspect ratio, straighten a video recorded sideways, crop black bars, or deinterlace broadcast footage.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| value | yes | aspect: "auto" | "16:9" | 1.78 · rotate: 0|90|180|270 · zoom: multiplier, 1 = fit · panscan: 0-1 · deinterlace: boolean |
Restore the file's own geometry — no aspect override, no rotation, no zoom or pan-scan, deinterlace off.
No parameter schema on file.
Read or set incognito mode. While on, nothing is written to the play history — including plays started from the CLI or by you. Call with no arguments to read it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| enabled | boolean | no | — |
Recently played files, newest first, with how many times each was played and when. Covers files opened directly, not just ones scanned into the library.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many to return (1-200, default 20) |
Forget the play history. Scanned library metadata is kept — only the played-at times and counts are cleared.
No parameter schema on file.
Save a named position in a file, so it can be jumped back to later. Defaults to where playback is right now in the file the user is watching. Bookmarks persist across sessions and are recorded even in incognito mode, since they are asked for explicitly.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Label for the spot. Omit and it shows as its timestamp. |
| position | number | no | Seconds into the file. Defaults to the current position; required when bookmarking a file that isn't playing. |
| file | string | no | Path or URL. Defaults to what's playing. |
Bookmarks for the file being watched, in timeline order. Pass all=true for every file, or file to ask about a specific one. Each entry carries the id that bookmark_goto takes, and the key it is filed under — the path for a file, the disc's own identity for a disc.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | no | Path or URL. Defaults to what's playing. A drive path resolves to the disc currently in it. |
| key | string | no | Exactly this identity, unresolved — from disc_list, get_status, or the key on a listed bookmark. Use it to reach bookmarks left under a drive letter before discs had an identity. |
| all | boolean | no | Every file instead of just one. |
Jump to a bookmark by id. Seeks if its file is already playing; otherwise opens that file at the bookmarked position, saving a resume point for the outgoing one. A bookmark on a disc is refused, without loading anything, when that disc is not the one in the drive.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Bookmark id from bookmark_list |
Give a bookmark a name, or drop the one it has by omitting name.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Bookmark id from bookmark_list |
| name | string | no | New label. Omit to remove the name. |
Delete one bookmark by id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | integer | yes | Bookmark id from bookmark_list |
Delete every bookmark for the file being watched, or for the file named. Pass all=true to delete them for every file — that scope is never reached by default.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| file | string | no | Path or URL. Defaults to what's playing. A drive path resolves to the disc currently in it. |
| key | string | no | Exactly this identity, unresolved — from disc_list, get_status, or the key on a listed bookmark. This is how bookmarks orphaned under a drive letter are deleted. |
| all | boolean | no | Every bookmark, for every file. |
List mouse bindings: wheel up/down, click, double click, middle click, and the four right-drag gestures, each with the action it runs.
No parameter schema on file.
Point a mouse trigger at an action. Unlike keys, two triggers may share an action — wheel-up and drag-up both raising volume is fine, since the inputs are distinct. Pass "none" as the action to disable a trigger.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trigger | string | yes | Trigger id from mouse_list, e.g. wheel_up, gesture_left |
| action | string | yes | Action id from keybind_list, or "none" |
Restore a mouse trigger to its default. Omit trigger to reset all of them.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| trigger | string | no | — |
List installed mpv user scripts (.lua and .js) in the config scripts folder, with each script's path, language, description, and whether it is enabled.
No parameter schema on file.
Install a .lua or .js mpv user script into the config scripts directory, enable it, and load it into the running player immediately.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path to the .lua or .js script file to install |
Enable or disable an installed mpv user script by filename (e.g. "autocrop.lua") or stem ("autocrop"). Enabling loads the script immediately; disabling takes effect on the next launch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Script filename or stem |
| enabled | boolean | yes | True to enable, false to disable |
Delete an installed mpv user script from the config scripts directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Script filename or stem to remove |
Return the frame showing right now as an image, so you can see what is on screen. Optionally seek to a position first. The picture is the one the viewer is watching — GUI, CLI and MCP share a single player. Downscaled to keep the response small; subtitles and on-screen controls are not burned in.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| position | number | no | Seek here (seconds) before capturing |
| max_edge | integer | no | Longest edge in pixels (64-2048, default 768) |
List all speakers in the transcript with cue count, word count, speaking duration, and first/last timestamp. Pass detect: true to run lightweight acoustic + conversational turn diarization when subtitles do not already carry speaker labels.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| detect | boolean | no | Run automatic speaker diarization if true (default false) |
| count | integer | no | Target number of speakers when detect=true (2-8) |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Rename a speaker label across the transcript (e.g. from "Speaker 1" to "Host" or "Alice"). The rename is persisted in cache so subsequent transcript_get, search_transcript, and transcript_summary calls reflect it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | Existing speaker name to replace |
| to | string | yes | New speaker name |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Export the transcript to a formatted string or file in txt, srt, vtt, or json format, optionally filtered to a single speaker.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| output | string | no | Optional output file path. Omit to receive the formatted text in the response. |
| format | string | no | Output format (default txt) |
| speaker | string | no | Optional speaker filter |
| file | string | no | Optional path to a video or subtitle file; defaults to the playing file |
Sample a grid of frames (cols × rows) evenly across a time range of the video and return a single tiled JPEG image plus the exact timestamp of every cell. Ideal for surveying what visually happens across a video or section in one multimodal tool call instead of calling describe_frame a dozen times.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cols | integer | no | Grid columns (1-6, default 4) |
| rows | integer | no | Grid rows (1-6, default 3) |
| start | number | no | Start time in seconds (default 0) |
| end | number | no | End time in seconds (default: file duration) |
| max_edge | integer | no | Target sheet width in pixels (256-2048, default 1280) |
| file | string | no | Optional video file path; defaults to the playing file |
Detect visual scene cuts / shot boundaries in the video using ffmpeg's scene-change filter. Useful for videos without dialogue or transcripts (screen recordings, silent footage, music videos). Set to_chapters: true to immediately install the detected scenes as navigable chapters on the playing…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| threshold | number | no | Scene change sensitivity threshold between 0.05 and 0.95 (default 0.3; lower detects more subtle cuts) |
| max_scenes | integer | no | Maximum number of scenes to return (1-100, default 20) |
| to_chapters | boolean | no | Apply detected scenes as virtual chapters on the playing file |
| file | string | no | Optional video file path; defaults to the playing file |
Save the current playlist to an .m3u, .m3u8, or .pls file.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Destination file path (.m3u, .m3u8, or .pls) |
Load an .m3u, .m3u8, or .pls playlist file into the player's queue. Relative paths inside the playlist are resolved against the playlist file's directory.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Path to the .m3u, .m3u8, or .pls playlist file |
| append | boolean | no | Append to the existing playlist instead of replacing it (default false) |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install unflick or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.1. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish unflick can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.