@tmhs/screencast-mcp
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 1 of 5 tools tried
Contacts while installing and starting: nothing
Its tool definitions changed since version 0.49.1. If you approved the earlier ones, read them again.
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y @tmhs/screencast-mcp@0.51.1
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 1 returned a result.
list_sessions | Returned a result under 0.1 s · 34 characters |
read_events | No usable answer tool reported an error: Pass sessionId or input. |
find_text | No usable answer tool reported an error: Required ffmpeg and ffprobe not found on PATH. ffmpeg and ffprobe must be installed and on PATH (or set FFMPEG_PATH / FFPROBE_PATH). Wi |
list_audio_devices | No usable answer tool reported an error: Required ffmpeg and ffprobe not found on PATH. ffmpeg and ffprobe must be installed and on PATH (or set FFMPEG_PATH / FFPROBE_PATH). Wi |
list_video_devices | No usable answer tool reported an error: Required ffmpeg and ffprobe not found on PATH. ffmpeg and ffprobe must be installed and on PATH (or set FFMPEG_PATH / FFPROBE_PATH). Wi |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
start_recording target, exactTitle, fps, quality, audio, output, overwrite, maxDurationSec, events, keys, focus, logs, perf, hotkeys, elements, cursor, backend, encoder, webcam, replayBufferSec, startWhen, stopWhen
Start a background screen recording. Returns a session id; finalize it with stop_recording. Never auto-starts.
stop_recording sessionId, save
Stop a recording gracefully so the file is finalized; returns the path and duration.
delete_recording sessionId, input
Delete a finished recording with its sidecars (event log, webcam, transcript, index, markers, pause parts) and registry entries; reports bytes freed. Asks the user first when the client supports it. Edits made from it are kept.
pause_recording sessionId
Pause a recording; until resume_recording nothing is captured, and the gap is left out of the file, events, and markers.
resume_recording sessionId
Resume a paused recording (same target and settings).
56 more tools
save_replay sessionId, lastSec, output, overwrite, reencode
Save the last N seconds of a replay buffer (start_recording replayBufferSec) to an mp4; the buffer keeps running.
list_sessions
List all recording sessions (active and finished) with their status, target, output path, and whether the process is still alive.
get_session sessionId
Inspect a single recording session by id, including live status and whether its output file exists on disk.
read_events sessionId, input, from, to, types, inFrameOnly, limit
Read the input events (clicks, scroll, cursor, shortcuts, typing bursts) of a recording made with events: true, in video seconds and pixels; e.g. types: ['down'], then sample_frames there.
add_marker label, sessionId, input, at
Mark a labelled moment on a recording, live or at a second. Kept in the session and a sidecar; chapters and pipeline turn markers into chapters.
review_recording input, sessionId
Open a recording for a person to review: in MCP Apps clients an inline player to scrub, trim, and redact, then export; elsewhere just the video's details.
screenshot target, exactTitle, backend, output, overwrite, returnImage, maxImageWidth
Capture one PNG of the screen, a monitor, a window, or a region, returned inline and by path.
sample_frames input, mode, fps, timestamps, sceneThreshold, dedupe, outputDir, maxFrames, returnImages, maxInlineImages, maxImageWidth
Sample PNG frames from a video (by fps, timestamps, or scene changes) and return the first few inline so the model can see what happened.
contact_sheet input, count, mode, sceneThreshold, columns, tileWidth, poster, output, overwrite, returnImage, maxImageWidth
Tile timestamped frames of a video into one image to see a whole recording at a glance (the cheapest first look).
screen_diff a, b, pixelThreshold, returnImage
Compare two screenshots or frames: SSIM score, changed share, and changed boxes in b's pixels, to check a UI change happened only where expected.
wait_for_change target, exactTitle, mode, text, regex, gone, backend, timeoutSec, settleSec, intervalMs, pixelThreshold, returnImage, keep
Wait until part of the screen changes, settles, or shows (or loses) some text, instead of guessing a sleep. Returns the elapsed time, changed regions (screenshot pixels; add `origin` for desktop), and the final state.
find_text target, input, timestamp, scanEverySec, maxFrames, exactTitle, backend, query, regex, redact, keep, returnImage
OCR (built into Windows) on the screen, an image, or video frames, with line and match boxes in image pixels (add `origin` for desktop coordinates). Locate UI text or secrets (e.g. regex 'sk-|ghp_|api.?key') to redact. Best-effort: review results.
index_recording input, sessionId, sceneThreshold, maxFrames, transcript, force
Build a recording's text timeline (<video>.index.json: OCR per scene, events, markers, transcript) for search_recording.
search_recording input, sessionId, query, regex, limit, images
Search an index_recording timeline (screen text, events, markers, transcript): timecoded hits, best first, secrets masked. No frames unless asked. No input: search all indexes.
get_media_info input
Probe a media file with ffprobe and return duration, resolution, frame rate, codecs, container format, and size.
trim input, start, end, duration, exact, output, overwrite
Cut a video down to one sub-clip by start + (end or duration). For several segments use clip; to combine with other edits use pipeline.
concat inputs, output, overwrite
Join videos end to end with hard cuts: stream copy when they match, else a re-encode (`mode` says which). For transitions use xfade_transition or assemble_highlights.
convert input, format, fps, width, output, overwrite
Convert media to mp4, webm, or gif. For a size-bounded GIF/WebP prefer export_gif; for a smaller mp4, compress or export_preset.
export_gif input, format, maxBytes, fps, width, start, duration, output, overwrite
Export an animated GIF or WebP that fits a size budget (for PRs, issues, READMEs), stepping fps, width, and quality down until it fits.
crop input, x, y, width, height, output, overwrite
Crop a video to a pixel rectangle; one running off the frame is rejected.
scale input, width, height, output, overwrite
Resize a video to a target width and/or height and re-encode. Provide one side to keep the aspect ratio, or both to set an exact size.
speed input, factor, segments, output, overwrite
Change playback speed, or fast-forward ranges, and re-encode. Audio is retempo'd to match.
overlay input, overlay, x, y, width, height, start, end, shape, output, overwrite
Composite an image or video (logo, watermark, picture-in-picture) onto a video at a pixel position, optionally scaled and time-limited; keeps the base's audio and length.
compose inputs, layout, alignMarker, endWith, audio, output, overwrite
Lay 2-9 videos out side by side, stacked, or in a grid (before/after, app and terminal), labelled and in sync.
perf_overlay input, perf, metric, corner, width, output, overwrite
Draw a recording's CPU or memory track as a small chart with a moving playhead (spikes in red).
translate_subtitles input, language, translations, output, overwrite
Translate an SRT without breaking its timing: call once for the numbered cues, translate them, then call with translations to write <input>.<language>.srt for chapters' subtitleTracks.
callout input, items, fontFile, output, overwrite
Annotate a video or screenshot with timed boxes, text labels, and arrows. Fallback fonts used are listed in fallbackFonts; characters no font covers are reported in warnings.
keystroke_overlay input, events, clicks, typing, keys, lingerSec, position, size, color, fontFile, dryRun, output, overwrite
Burn keycast-style badges for shortcuts, clicks, and typing from the recording's input event log (start_recording events: true). Never shows typed text: the log has none.
cursor input, events, size, smoothing, hideAfterSec, clicks, spotlight, dryRun, output, overwrite
Draw a smoothed, scaled cursor that hides when idle from the event log of a start_recording cursor: "events" recording (no OS cursor in the video), with click ripples and an optional spotlight.
backdrop input, preset, colors, image, padding, radius, shadow, shadowOpacity, aspect, output, overwrite
Frame a video or screenshot on a gradient, color, or wallpaper with padding, rounded corners, and a drop shadow, optionally on a 16:9/1:1/9:16/4:5 canvas.
compress input, level, maxWidth, output, overwrite
Re-encode a video smaller (H.264 CRF ladder, optional width cap). For a platform target use export_preset.
extract_audio input, format, output, overwrite
Extract the audio track of a media file to its own file (mp3, aac, wav, or copy). Returns the output path.
normalize_audio input, target, output, overwrite
Normalize loudness to a delivery target (two-pass EBU R128 loudnorm); video is copied. Reports loudness before and after.
denoise input, strength, output, overwrite
Reduce steady background noise (fan, hum, hiss) in a recording's audio with an adaptive FFT denoiser. Video is copied untouched. Returns the output path.
transcribe input, model, language, words, output, overwrite
Transcribe a recording's speech to an SRT subtitle file, locally, with FFmpeg 8's whisper filter (needs a whisper.cpp model file). Returns the SRT path and the text. Pair with burn_subtitles to caption the video.
burn_subtitles input, subtitles, style, output, overwrite
Burn SRT/ASS subtitles (e.g. from transcribe) into a video in the bundled font.
chapters input, sessionId, from, chapters, transcript, minChapterSec, subtitles, subtitleLanguage, subtitleTracks, textOnly, output, overwrite
Write chapters (markers, scene changes, transcript, or a list) into an mp4/mkv/mov copy without re-encoding; returns YouTube chapter text. Can mux an SRT as soft subtitles.
clip input, segments, output, overwrite
Extract several frame-exact segments, each to its own file. For one segment, trim does the same.
cut_idle input, minIdleSec, keepSec, useAudio, action, factor, dryRun, output, overwrite
Remove dead air: cut stretches where the screen is frozen (and silent), keeping a short pad. Returns the time saved.
cut_by_transcript input, srt, remove, fillers, dryRun, output, overwrite
Edit a video by its transcript: cut quoted text, cue numbers, or fillers. Also writes the re-timed .srt.
redact_region input, regions, style, pad, color, output, overwrite
Cover given rectangles in a video or screenshot (e.g. secrets on screen). Not automatic detection: find them with find_text redact: true. Off-frame regions are rejected.
list_audio_devices
List DirectShow audio devices and flag a likely loopback (Stereo Mix or a virtual-audio driver), for start_recording's audio.device.
list_video_devices
List DirectShow cameras for start_recording's webcam.device.
list_targets exe, titleContains, capturableOnly
List the desktop, monitors, and visible windows (topmost first, with capturability per backend). Each entry has a `target` string to pass as-is to capture tools; use it instead of guessing a title.
doctor
Check the setup: ffmpeg/ffprobe (FFmpeg 8+?), optional filters, capture devices, Windows OCR, settings, and enabled toolsets; `problems` says what is missing and how to fix it. Call on first use or when a tool reports a missing feature.
xfade_transition inputA, inputB, transition, duration, output, overwrite
Join two videos with an xfade transition (audio crossfaded); they need not match in size, fps, or audio. For more clips use assemble_highlights.
assemble_highlights clips, transition, duration, width, height, fps, output, overwrite
Stitch clips (including title cards) into one video with cuts or xfade transitions; they need not match in size, fps, or audio.
title_card text, duration, width, height, fps, bg, fontColor, fontSize, bold, fontFile, output, overwrite
Generate a title card clip (centered text on a solid background, silent audio track) to stitch in with assemble_highlights. Uncoverable characters are reported in warnings.
music_bed video, music, musicVolume, fadeIn, fadeOut, duck, output, overwrite
Lay music under a video: looped or trimmed to length, faded, leveled, and mixed with any existing audio. Video is stream-copied.
narrate video, lines, voice, rate, duck, output, overwrite
Offline voiceover with the built-in Windows voices: speaks each line at its time or marker over the audio, plus an SRT.
reframe input, aspect, fit, output, overwrite
Re-aspect a video to 16:9, 9:16, 1:1, or 4:5 by padding or cropping.
zoom input, keyframes, follow, events, highlightClicks, highlightColor, transitionSec, maxZoom, holdSec, dryRun, output, overwrite
Smooth animated zoom-and-pan into the action and back out, from keyframes or planned from logged clicks or screen changes.
pipeline input, fromEdit, steps, recipe, quality, dryRun, output, overwrite, chapters
Run several edits (trim, crop, scale, speed, cut_idle, redact, callout, keystroke_overlay, cursor, reframe, zoom, backdrop, audio, burn_subtitles, then optionally export_preset or export_gif) in one ffmpeg pass: one re-encode, no intermediate files. Prefer it over chaining edit tools; a recipe does the usual polish in one call.
export_preset input, platform, fit, output, overwrite
Encode a platform-ready H.264 file (aspect, fps, bitrate, faststart) for a named platform.
bug_report input, sessionId, title, actual, expected, start, end, clipSec, redact, secretPattern, regions, errorPattern, scanEverySec, maxFrames, gif, maxBytes, outputDir, overwrite
Package a recording as a paste-ready repro folder: secret-scanned, redacted clip and GIF, contact sheet, steps from the event log, OCR'd errors, environment, report.md for gh issue create --body-file.
step_guide input, sessionId, title, format, ocr, outputDir, overwrite
Turn a recording's event log into a numbered how-to: a ringed screenshot and caption per step, marker headings; Markdown and/or one HTML file. Never includes typed text.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | CC-BY-NC-ND-4.0 |
|---|---|
| Needs | node >=22.0.0 |
| Source | github.com/TMHSDigital/screencast-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-UW2ouUaBR8wK7hyDS0WZDnGuytbDBlCQZMrxS9IPB7i9C78HJq7H2Q7ovNu2WN7VfpGvnu/K7Siiks59p+/tAg== |
Versions reported
| Version | Run | Result | Tools |
|---|---|---|---|
| 0.51.1 | 2026-11-16 | Starts with no setup | 61 |
| 0.49.1 | 2026-11-12 | Starts with no setup | 58 |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/%40tmhs/screencast-mcp)
New version out? Ask for a fresh report.