# io.github.AudialAI/audial-mcp (pypi · audial-mcp)

Audial audio tools: stems, analysis, mastering, sample packs, MIDI, music generation, vocals.

- Trust score: 80/100 (high trust)
- Change this week: −4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

> **Recent critical change**: GHSA-6q48-6c7w-9gw2 affects this package (2026-10-21). See the changelog below before you install this server.

## Components

- pypi · `audial-mcp`: 80/100 (this document), [markdown](https://verifymcp.io/servers/audialai-audial-mcp/audial-mcp.md), [page](https://verifymcp.io/servers/audialai-audial-mcp/audial-mcp)

## Channel facts

- Registry: `pypi`
- Package: `audial-mcp`
- Version: `0.5.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 2 of 38 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3205 tokens (~200/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the io.github.AudialAI/audial-mcp server?

io.github.AudialAI/audial-mcp runs locally as a PyPI package, launched with uvx audial-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add audialai-audial-mcp -- uvx audial-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "audialai-audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "audialai-audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add audialai-audial-mcp -- uvx audial-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "audialai-audial-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "audial-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add audialai-audial-mcp --command uvx --arg audial-mcp
```

### Hermes

```yaml
mcp_servers:
  audialai-audial-mcp:
    command: "uvx"
    args: ["audial-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "audialai-audial-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "audial-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add audialai-audial-mcp -t stdio -c uvx -a audial-mcp
```

### Other

```json
{
  "mcpServers": {
    "audialai-audial-mcp": {
      "command": "uvx",
      "args": [
        "audial-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 80, −3)

- [functional] Stability: pass → 0.77

### 2026-10-31 (score 83, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-30 (score 68, −16)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: 148 → 200
- [functional] Package version: 0.1.1 → 0.5.0

### 2026-10-29 (score 84, +1)

- [security] Stability: 0.97 → pass

### 2026-10-27 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 82, +1)

- [security regression] Provenance: unverified → fail

### 2026-10-24 (score 81, 0)

- [security regression] Provenance: fail → unverified

### 2026-10-23 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (16)

### `stem_split` (~227 tokens)

Split stems

Split a track into separate instrument stems, optionally retimed and rekeyed.

Use for a full song or mix when the user wants vocals, drums, bass or an instrumental on
their own. For tempo and key alone use analyze; for sections use segment. Takes a few
minutes and counts as one run. Stems go to a new results folder; the source is unchanged.

Input parameters:

- `algorithm` (string): Separation algorithm. Default 'primaudio'.
- `file_path` (string, required): Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.
- `stems`: Stems to extract from: vocals, drums, bass, other, full_song_without_vocals. Default: vocals, drums, bass, other.
- `target_bpm`: Retime the stems to this tempo (beats per minute).
- `target_key`: Transpose the stems to this key, e.g. 'A minor' or 'F# major'.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `analyze` (~122 tokens)

Analyze audio

Analyze a track: BPM, key, loudness and other characteristics.

Use this first whenever the user asks for tempo, key or loudness. It is the fastest tool
(seconds), does not count as a run, and changes nothing. The answer is in `metadata` and
the same data is saved to the results folder.

Input parameters:

- `file_path` (string, required): Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `segment` (~202 tokens)

Segment audio

Detect song sections (intro, verse, chorus...) and analyze components within them.

Use for song structure. For tempo and key alone use analyze. Runs the `segmentation`
pipeline: splits stems, then segments them; one call, counted as one run. Tempo and key
are detected automatically. Takes a few minutes and each step is reported as it starts and
finishes. If the call times out the job keeps running: pipeline_status finds it.

Input parameters:

- `analysis_type`: Analysis type accepted by Audial's segmentation.
- `components`: Components to analyze, e.g. ['vocals', 'drums'].
- `features`: Features to compute per segment.
- `file_path` (string, required): Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.
- `genre`: Genre hint that improves section detection.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `master` (~131 tokens)

Master a track

Master a mix, optionally matching a reference track.

Use for a finished stereo mix, not for separate stems. Pass a reference track when the user
names one. Takes a few minutes and counts as one run. The master goes to a new results
folder; the source is unchanged.

Input parameters:

- `file_path` (string, required): Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.
- `reference_file`: Optional reference track whose loudness and tone the master should match.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `generate_samples` (~208 tokens)

Generate a sample pack

Extract a sample pack (one-shots and loops) from a track.

Use when the user wants drum hits or loops taken from a finished track. Runs the
\`sample-pack` pipeline: splits stems, then builds the sample pack; one call, counted as one
run. Tempo and key are detected automatically. Takes a few minutes and each step is reported
as it starts and finishes. If the call times out the job keeps running: pipeline_status
finds it. Samples go to a new results folder.

Input parameters:

- `components`: Which components to sample, e.g. ['drums', 'bass'].
- `file_path` (string, required): Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.
- `genre`: Genre hint.
- `job_type`: Sample pack job type accepted by Audial (default engine choice when omitted).

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `generate_midi` (~123 tokens)

Audio to MIDI

Transcribe an audio file to MIDI.

Use to get notes out of audio. On a full mix, run stem_split first and transcribe the stem
you want. Counts as one run. MIDI files go to a new results folder; the source is unchanged.

Input parameters:

- `bpm`: Override the detected tempo for note quantisation.
- `file_path` (string, required): Full path to a local audio file (.wav, .mp3, .aif, .aiff, .flac, .m4a, .ogg, .aac). ~ is expanded.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `generate_music` (~414 tokens)

Generate music

Generate music with the Audial music model.

Text to music, covers, remixes, lego (re-render with one track emphasised),
or analysis (understand). Use for new or transformed music, not to edit an existing mix:
that is master or stem_split. Takes a few minutes and counts as one run, and audio goes to
a new results folder.

Input parameters:

- `audio_cover_strength`: 0-1 fidelity to the original for cover/remix.
- `audio_duration`: Length in seconds (10-600).
- `audio_format` (string): mp3, wav, flac, opus or aac.
- `batch_size` (integer): Number of variations, 1-8.
- `bpm`: Tempo hint in beats per minute.
- `instrumental` (boolean): Generate without vocals.
- `key_scale`: Key hint, e.g. 'G major'.
- `lyrics`: Lyrics with optional section tags like [Verse] and [Chorus]. Omit for instrumental.
- `negative_prompt`: What to avoid, comma-separated.
- `prompt` (string, required): Style description: genre, mood, instruments, vocal character. Tempo and key words in the prompt steer the model more than the numeric bpm/key fields, which are hints, not constraints.
- `reference_file`: Local audio file; required for cover.
- `repainting_end`: Remix end time in seconds (-1 = end).
- `repainting_start`: Remix start time in seconds.
- `seed`: Seed for reproducible output.
- `source_file`: Local audio file; required for remix, lego, understand.
- `task_type` (string): text2music (default), cover, remix, lego, or understand.
- `time_signature`: e.g. '4/4'.
- `track_name`: Track to emphasise for lego: vocals, drums, bass, guitar, piano, strings, synth, other.
- `vocal_language` (string): Language code for vocals, e.g. 'en'.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `sound2vital` (~152 tokens)

Resynthesize a one-shot into a synth preset

Turn one isolated sound into an editable Audial Synth preset.

Not for loops or melodies, which give a poor preset. If the result's summary says the match
is weak, tell the user and suggest trimming the input to one note.

Input parameters:

- `file_path` (string, required): One isolated sound: a single note, chord stab or hit, ideally 1-4 s and dry, 20 s at most. Not a loop, melody, drum pattern or anything with several notes in sequence: those produce a poor preset eve…

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `sound2serum` (~171 tokens)

Resynthesize a one-shot into a Serum 2 preset

Turn one isolated sound into an editable Xfer Serum 2 preset.

Not for loops or melodies, which give a poor preset. If the result's summary says the match
is weak, tell the user and suggest trimming the input to one note.

Input parameters:

- `file_path` (string, required): One isolated sound: a single note, chord stab or hit, ideally 1-4 s and dry, 20 s at most. Not a loop, melody, drum pattern or anything with several notes in sequence: those produce a poor preset eve…

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `text2vox` (~568 tokens)

Sing lyrics in a reference voice

Synthesize a sung vocal (and MIDI) from lyrics, a melody and a reference voice.

Needs both a reference clip of the voice and a melody, as MIDI or audio. lyrics_mode decides
how the lyrics are lined up with the melody's notes; "per_note" is the one that gives exact
control. See the lyrics_mode and lyrics descriptions. Takes a few minutes and counts as one
run. Audio and MIDI go to a new results folder.

Input parameters:

- `bend_smoothing_ms`: Pitch-bend smoothing window in ms.
- `cfg_strength`: Guidance strength.
- `leading_silence_s`: Silence before the first note, seconds.
- `lyrics` (string, required): Lyrics to sing. With lyrics_mode 'per_note' this is pipe-delimited, one token per MIDI note, e.g. 'amazing|-|-|grace|-|how|sweet|the|sound'; otherwise it is ordinary text.
- `lyrics_mode` (string): How the lyrics line up with the melody. 'auto' (default): ordinary text, one word per MIDI note, aligned for you (word_timestamps_file helps). '1to1': the text is passed to the synthesizer untouched.…
- `melody_audio_file`: Audio whose melody is transcribed and followed, if no MIDI.
- `midi_file`: MIDI melody (.mid). Give this or melody_audio_file.
- `nfe_steps`: Synthesis steps; more is slower and cleaner.
- `no_pitch_bends`: Disable pitch bends.
- `pitch_shift`: Semitones to shift the melody.
- `reference_file` (string, required): Short clip of the reference voice (timbre).
- `reference_text`: Transcript of the reference clip, if known.
- `seed`: Seed for reproducible output.
- `strict_pitch`: Force exact pitch to the melody.
- `word_timestamps_file`: Optional JSON word timings.

Output parameters:

- `execution_id`
- `files` (array)
- `metadata` (object)
- `output_dir` (string)
- `summary` (string)
- `tool` (string)

### `service_status` (~175 tokens)

Service status

Which Audial tools have a worker awake right now, and what a cold one will cost.

Audial's GPU workers scale to zero. A tool reported `warm: false` will spend
\`expectedColdStartMs` starting a worker before it does any work -- a few minutes, once --
on top of the job's own `expectedRunMs`. Worth checking before starting a long job, and
worth telling the user about with the `notice` text when something is cold: otherwise the
wait looks like a hang. Nothing here starts a job or costs anything.

Input parameters:

- `tool`: Audial tool to report on: stem_split, analyze, segment, master, generate_samples, generate_midi, generate_music, sound2vital, sound2serum or text2vox. Omit for all of them.

### `pipeline_status` (~83 tokens)

Pipeline status

Look up an Audial pipeline by id: its state, each step, and the outputs so far.

Useful when a segment or generate_samples call timed out: the pipeline keeps running on
Audial's side and this says how far it got.

Input parameters:

- `pipeline_id` (string, required): Id of a pipeline, as returned in `execution_id` by segment or generate_samples.

### `list_results` (~86 tokens)

List previous results

List previous Audial results in the results folder, newest first.

Use when the user asks where an earlier output went. Reads the local folder only: no account
needed and nothing is sent anywhere.

Input parameters:

- `limit` (integer): Maximum number of jobs to return, newest first.
- `tool`: Filter by tool name, e.g. 'stem_split'. Omit for all tools.

Output parameters:

- `result` (array)

### `account` (~45 tokens)

Show the Audial account in use

Show whether this computer is signed in to Audial, and as whom.

Use when a tool reports a credentials problem or the user asks which account is in use.
Reads local settings only.

Output parameters:

- `email`
- `signed_in` (boolean)
- `source`: Where the credentials come from: 'sign-in' or 'api-key'.
- `summary` (string)

### `sign_in` (~67 tokens)

Sign in to Audial

Sign in to Audial through the user's browser. Opens an approval page and waits for it.

Not needed before other tools: they start the same sign-in when nobody is signed in.

Input parameters:

- `switch_account` (boolean): Sign out first and sign in again, to change or repair the account.

Output parameters:

- `email`
- `signed_in` (boolean)
- `source`: Where the credentials come from: 'sign-in' or 'api-key'.
- `summary` (string)

### `sign_out` (~54 tokens)

Sign out of Audial

Sign out of Audial on this computer and disconnect it from the account.

Only when the user asks to sign out or switch accounts. The next job asks them to sign in
again. Results already downloaded stay where they are.

Output parameters:

- `email`
- `signed_in` (boolean)
- `source`: Where the credentials come from: 'sign-in' or 'api-key'.
- `summary` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/audialai-audial-mcp/audial-mcp#diagnostics

## Score history

- 2026-11-05: 80
- 2026-11-04: 80
- 2026-11-03: 83
- 2026-11-02: 83
- 2026-11-01: 83
- 2026-10-31: 83
- 2026-10-30: 68
- 2026-10-29: 84
- 2026-10-28: 83
- 2026-10-27: 83
- 2026-10-26: 82
- 2026-10-25: 82
- 2026-10-24: 81
- 2026-10-23: 81
- 2026-10-22: 80
- 2026-10-21: 0
- 2026-10-20: 79
- 2026-10-19: 79
- 2026-10-18: 78
- 2026-10-17: 78
- 2026-10-16: 78
- 2026-10-15: 77
- 2026-10-14: 77
- 2026-10-13: 76
- 2026-10-12: 76
- 2026-10-09: 55
- 2026-10-06: 70
- 2026-10-05: 70
- 2026-10-04: 70
- 2026-10-03: 70

## Common questions

### What is the io.github.AudialAI/audial-mcp server?

io.github.AudialAI/audial-mcp is listed in the public MCP registry as io.github.AudialAI/audial-mcp. Audial audio tools: stems, analysis, mastering, sample packs, MIDI, music generation, vocals. This page covers its PyPI package (audial-mcp).

### Is the io.github.AudialAI/audial-mcp server safe to use?

io.github.AudialAI/audial-mcp scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.AudialAI/audial-mcp server expose?

io.github.AudialAI/audial-mcp exposes 16 tools: stem_split, analyze, segment, master, generate_samples, and 11 more. Their descriptions and schemas cost roughly 2,828 tokens of context every time the server is loaded.

### Is the io.github.AudialAI/audial-mcp server still maintained?

io.github.AudialAI/audial-mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.AudialAI/audial-mcp server under?

io.github.AudialAI/audial-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/audial-mcp/
- Socket report: https://socket.dev/pypi/package/audial-mcp
- Repository: https://github.com/AudialAI/audial-mcp
- Website: https://audialmusic.ai/resources/api-reference
- Changelog RSS feed: https://verifymcp.io/servers/audialai-audial-mcp/audial-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/audialai-audial-mcp/audial-mcp.json
- HTML version of this page: https://verifymcp.io/servers/audialai-audial-mcp/audial-mcp