Agent-first multitrack audio editor for the web: people and AI agents edit the same session live, over UI, REST and MCP.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
NYXMIX_TOKENAPI keyoptionalBearer token required for API/MCP access (recommended when reachable by others)
Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
archive_urlGet a download URL for a .nyxmix archive of the session (project, lossless audio, transcripts, versions, and the custom plugins it uses) — for backups or moving the session to another NyxMix server, where POST /api/projects/import restores it.Get a download URL for a .nyxmix archive of the session (project, lossless audio, transcripts, versions, and the custom plugins it uses) — for backups or moving the session to another NyxMix server, where POST /api/projects/import restores it.
No input schema was published for this tool.
batch_processRun one destructive process (see process_audio kinds, e.g. loudness, denoise, voiceDenoise, declip) on several files — by default every file used on the timeline. Each result is swapped into its clips when the length stays the same. Returns per-file results.Run one destructive process (see process_audio kinds, e.g. loudness, denoise, voiceDenoise, declip) on several files — by default every file used on the timeline. Each result is swapped into its clips when the length stays the same. Returns per-file results.
No input schema was published for this tool.
stretch_clipTime-stretch one clip to an exact length (duration in seconds) or by a ratio, keeping its pitch (Rubber Band, high quality) — e.g. fit a music bed to 30.0 s. Creates a new file and points the clip at it; one undo step.Time-stretch one clip to an exact length (duration in seconds) or by a ratio, keeping its pitch (Rubber Band, high quality) — e.g. fit a music bed to 30.0 s. Creates a new file and points the clip at it; one undo step.
No input schema was published for this tool.
export_cdExport a CD image (Audition: CD Layout): 44.1 kHz/16-bit dithered WAV plus a CUE sheet. Every labelled marker starts a CD track (titles from labels, min 4 s apart, up to 99). Burn the .cue with any burning program.Export a CD image (Audition: CD Layout): 44.1 kHz/16-bit dithered WAV plus a CUE sheet. Every labelled marker starts a CD track (titles from labels, min 4 s apart, up to 99). Burn the .cue with any burning program.
No input schema was published for this tool.
check_deliveryNo description publishedThis tool published no description. Forge does not invent one.
convert_sample_rateChange the session sample rate (44100, 48000, 88200, 96000): every file is resampled with SoX (high quality); clip times and the arrangement stay the same. Not undoable — save_version first if unsure.Change the session sample rate (44100, 48000, 88200, 96000): every file is resampled with SoX (high quality); clip times and the arrangement stay the same. Not undoable — save_version first if unsure.
No input schema was published for this tool.
auto_duckLower a music/bed track automatically wherever the voice tracks are speaking. Writes volume automation on the music track (replacing its existing volume automation) — one undoable step; the human can fine-tune the points afterwards. Returns the detected speech regions.Lower a music/bed track automatically wherever the voice tracks are speaking. Writes volume automation on the music track (replacing its existing volume automation) — one undoable step; the human can fine-tune the points afterwards. Returns the detected speech regions.
No input schema was published for this tool.
install_faust_pluginprivilegedNo description publishedThis tool published no description. Forge does not invent one.
generate_audioNo description publishedThis tool published no description. Forge does not invent one.
list_lv2_pluginsSearch the native effect plugins installed on the server — LV2 and VST3 (LSP, x42, Calf, ZAM, Dragonfly, DISTRHO, MDA, …: EQs, compressors, limiters, gates, reverbs, delays, filters, distortion, modulation, stereo tools). They run server-side as destructive processes via apply_lv2_plugin. Filter by…Search the native effect plugins installed on the server — LV2 and VST3 (LSP, x42, Calf, ZAM, Dragonfly, DISTRHO, MDA, …: EQs, compressors, limiters, gates, reverbs, delays, filters, distortion, modulation, stereo tools). They run server-side as destructive processes via apply_lv2_plugin. Filter by…
No input schema was published for this tool.
lv2_plugin_infoControls of one LV2 or VST3 plugin (by uri or #index from list_lv2_plugins): symbol, label, range, unit, default, toggles and enumerations. Pass values by symbol in apply_lv2_plugin.controls; anything not passed keeps its default.Controls of one LV2 or VST3 plugin (by uri or #index from list_lv2_plugins): symbol, label, range, unit, default, toggles and enumerations. Pass values by symbol in apply_lv2_plugin.controls; anything not passed keeps its default.
No input schema was published for this tool.
apply_lv2_pluginNo description publishedThis tool published no description. Forge does not invent one.
list_projectsList editing sessions.List editing sessions.
No input schema was published for this tool.
create_projectCreate an empty session.Create an empty session.
No input schema was published for this tool.
get_projectRead the session: tracks, clips (with times), effects, assets, markers. format "summary" (default) is compact text; "json" is the full document.Read the session: tracks, clips (with times), effects, assets, markers. format "summary" (default) is compact text; "json" is the full document.
No input schema was published for this tool.
describe_capabilitiesEffect types with parameter ranges, destructive processes, and export formats.Effect types with parameter ranges, destructive processes, and export formats.
No input schema was published for this tool.
import_audioAdd an audio file to the session bin from a public URL or base64 data. Any common format; converted losslessly to 32-bit float at the project rate. Returns the asset (id, duration). Then place it with clip.add.Add an audio file to the session bin from a public URL or base64 data. Any common format; converted losslessly to 32-bit float at the project rate. Returns the asset (id, duration). Then place it with clip.add.
No input schema was published for this tool.
editprivilegedNo description publishedThis tool published no description. Forge does not invent one.
undoUndo the last edit (by anyone).Undo the last edit (by anyone).
No input schema was published for this tool.
redoRedo.Redo.
No input schema was published for this tool.
analyzeMeasure audio: EBU R128 loudness (integrated LUFS, LRA, true peak), sample peak/RMS/clipping/DC, silent stretches, spectral band balance, optional RMS envelope.Measure audio: EBU R128 loudness (integrated LUFS, LRA, true peak), sample peak/RMS/clipping/DC, silent stretches, spectral band balance, optional RMS envelope.
No input schema was published for this tool.
get_imageRender a waveform or spectrogram PNG of the mix, an asset or a clip, so you can look at the audio.Render a waveform or spectrogram PNG of the mix, an asset or a clip, so you can look at the audio.
No input schema was published for this tool.
process_audioNo description publishedThis tool published no description. Forge does not invent one.
renderExport the mix. Returns a download URL plus measured loudness. bounce:true instead adds the mixdown to the bin as a new asset.Export the mix. Returns a download URL plus measured loudness. bounce:true instead adds the mixdown to the bin as a new asset.
No input schema was published for this tool.
get_activityRecent edits with author (human or agent) — use it to see what the human changed.Recent edits with author (human or agent) — use it to see what the human changed.
No input schema was published for this tool.
pitch_curveManual pitch correction: shift a voice by a curve of points {time (asset/source seconds), cents} — linear between points, 0 outside, so put 0-cent points around the part you fix. E.g. a note 30 cents flat from 12.40–12.90 s: [{time:12.3,cents:0},{time:12.4,cents:30},{time:12.9,cents:30},{time:13.0,…Manual pitch correction: shift a voice by a curve of points {time (asset/source seconds), cents} — linear between points, 0 outside, so put 0-cent points around the part you fix. E.g. a note 30 cents flat from 12.40–12.90 s: [{time:12.3,cents:0},{time:12.4,cents:30},{time:12.9,cents:30},{time:13.0,…
No input schema was published for this tool.
list_pluginsInstalled effect plugins (use them with effect.add type "plugin:<id>") and whether installing is enabled here.Installed effect plugins (use them with effect.add type "plugin:<id>") and whether installing is enabled here.
No input schema was published for this tool.
install_pluginprivilegedInstall a custom real-time effect: manifest {id, label, description, params:{name:{minimum,maximum,default,unit}}} plus code = an AudioWorklet module that calls registerProcessor("plugin-<id>", Class) with one k-rate AudioParam per param. It is test-rendered before it is accepted, then usable every…Install a custom real-time effect: manifest {id, label, description, params:{name:{minimum,maximum,default,unit}}} plus code = an AudioWorklet module that calls registerProcessor("plugin-<id>", Class) with one k-rate AudioParam per param. It is test-rendered before it is accepted, then usable every…
No input schema was published for this tool.
remix_musicMake a music clip fit a target length by jumping between musically similar beats (like Audition's Remix) instead of stretching: tempo and pitch stay untouched. Result is ordinary clips with crossfades at the jumps (one undo step), so a human can adjust them. Typical use: fit a bed to an episode or…Make a music clip fit a target length by jumping between musically similar beats (like Audition's Remix) instead of stretching: tempo and pitch stay untouched. Result is ordinary clips with crossfades at the jumps (one undo step), so a human can adjust them. Typical use: fit a bed to an episode or…
No input schema was published for this tool.
propose_editsSuggest a batch of edits WITHOUT applying them. The human hears a preview and accepts or rejects it in the UI. Use this for anything subjective or destructive-feeling (big cuts, re-ordering, heavy processing choices) or when the human asked to review first. Same op format as `edit`. label = one lin…Suggest a batch of edits WITHOUT applying them. The human hears a preview and accepts or rejects it in the UI. Use this for anything subjective or destructive-feeling (big cuts, re-ordering, heavy processing choices) or when the human asked to review first. Same op format as `edit`. label = one lin…
No input schema was published for this tool.
list_proposalsProposals for a session with their status (open, accepted, rejected) and who decided.Proposals for a session with their status (open, accepted, rejected) and who decided.
No input schema was published for this tool.
save_versionSave a named snapshot of the session (e.g. before a risky pass) that the human can return to.Save a named snapshot of the session (e.g. before a risky pass) that the human can return to.
No input schema was published for this tool.
spectral_editprivilegedNo description publishedThis tool published no description. Forge does not invent one.
noise_reductionNo description publishedThis tool published no description. Forge does not invent one.
get_pitchNo description publishedThis tool published no description. Forge does not invent one.
spectral_imageNo description publishedThis tool published no description. Forge does not invent one.
transcribeNo description publishedThis tool published no description. Forge does not invent one.
get_transcriptRead the TIMELINE transcript: words from every clip on unmuted tracks, mapped to timeline seconds (so it reflects all edits; re-read after cutting, because later times shift). format "text" (default): one line per phrase, "[start–end] words…" (with "Track:" when several tracks speak), filler words…Read the TIMELINE transcript: words from every clip on unmuted tracks, mapped to timeline seconds (so it reflects all edits; re-read after cutting, because later times shift). format "text" (default): one line per phrase, "[start–end] words…" (with "Track:" when several tracks speak), filler words…
No input schema was published for this tool.
cut_transcriptNo description publishedThis tool published no description. Forge does not invent one.
remove_filler_wordsprivilegedNo description publishedThis tool published no description. Forge does not invent one.
27 of 40 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Agent-first multitrack audio editor for the web: people and AI agents edit the same session live, over UI, REST and MCP.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
13 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+1 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.