# Audio (npm · audio)

Edit, analyze and convert audio: loudness, spec checks, denoise, EQ, cuts, BPM, key. No ffmpeg.

- Trust score: 73/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- npm · `audio`: 73/100 (this document), [markdown](https://verifymcp.io/servers/audiojs-audio/audio.md), [page](https://verifymcp.io/servers/audiojs-audio/audio)

## Channel facts

- Registry: `npm`
- Package: `audio`
- Version: `2.10.0`
- 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 2026-10-23.

- **Supply Chain Security**: 88/100
  - No malware found by supply-chain analysis.
  - Known CVEs were checked across the 182 of 268 dependencies we could resolve, so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Dependency health was assessed across the 182 of 268 dependencies we could resolve, so this covers what we could see, not the whole tree.
- **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 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 745 tokens (~745/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 1 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 Audio MCP server?

Audio runs locally as an npm package, launched with npx -y audio. 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 audiojs-audio -- npx -y audio
```

### Cursor

```json
{
  "mcpServers": {
    "audiojs-audio": {
      "command": "npx",
      "args": [
        "-y",
        "audio"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "audiojs-audio": {
      "command": "npx",
      "args": [
        "-y",
        "audio"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add audiojs-audio -- npx -y audio
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "audiojs-audio": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "audio"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add audiojs-audio --command npx --arg -y --arg audio
```

### Hermes

```yaml
mcp_servers:
  audiojs-audio:
    command: "npx"
    args: ["-y", "audio"]
```

### Netclaw

```json
{
  "McpServers": {
    "audiojs-audio": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "audio"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add audiojs-audio -t stdio -c npx -a -y audio
```

### Other

```json
{
  "mcpServers": {
    "audiojs-audio": {
      "command": "npx",
      "args": [
        "-y",
        "audio"
      ]
    }
  }
}
```

## 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.

### 2026-10-22 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-20 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 69, +5)

- [functional improvement] Stability: unverified → 0.37

### 2026-10-12 (score 64, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-11 (score 64, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-04 (score 64, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (1)

### `audio` (~745 tokens)

Audio

Shell: `npx -y audio ARGS`. MCP tool `audio`: same ARGS.

ARGS = SOURCE [OP ARGS]… [SINK]
\- SOURCE: path (audio/video), URL, `'*.wav'` (batch), `a.mp3 + b.wav` (concat), `record 10s` (mic)
\- SINK: `stat [NAMES]` (the default) · `check SPEC` · `save PATH [192k] [24bit]` (format by extension, `-f` overwrites; .mp4 keeps a video's picture; .edl/.fcpxml/.otio: cut list) · `play`
\- Units: `1.5s` `500ms` `1:30` · `-3db` · `80hz` `2khz` · band `1khz..4khz`. Range `10s..20s`, `-5s..` (last 5s): after an op: that op; alone: the output. Options: `name:value`.

Ops: trim [DB] · shrink [GAP] · normalize podcast|streaming|broadcast|DB [lufs|rms] · gain DB · fade IN -OUT · crop RANGE · remove RANGE [XFADE] · pad S · speed R · stretch F (2 = twice as long) · pitch SEMI · intonation F (0 monotone, 2 twice as wide) · formant SEMI (pitch kept) · highpass HZ [ORDER] · lowpass HZ · eq HZ DB [Q] · lowshelf/highshelf HZ DB · notch HZ · mix FILE [AT] [DB] · crossfade FILE S · remix 1|2 · resample HZ · dither 16 · match REF · master REF · roomtone (fill silence) · spectral BAND [DB] RANGE · repair RANGE · split T… (save `part-{i}.wav`). Plugins by name: compressor, limiter, deesser, dehum, declick, dereverb, ducker key:VOICE… `--help`: all ops; `OP --help`: params.

Stats: db peak rms noisefloor loudness momentary shortterm dialog truepeak lra dc clipping silence crest correlation bpm key chords notes; `spectrum 32`: 32 bins.

Measure, edit, verify:
1\. `in.wav`: levels, BPM, clipping, DC
2\. `in.wav trim normalize podcast check podcast`: preview, nothing written
3\. `in.wav trim normalize podcast save out.mp3`: writes a new file
4\. `out.mp3 check podcast`: ✓/✗ per rule; report a fail, don't hide it

Specs: podcast (Apple, -16 LUFS) · streaming (Spotify, -14) · broadcast (EBU R 128, -23) · netflix (dialog -27, ≤ -2 dBTP) · acx (audiobook). normalize holds ≤ -1 dBTP (`ceiling:-2`). ACX: `omlsa compressor -24 2.5 normalize -20 rms ceiling:-3.5 trim pad 1.5s 2s roomtone resample 44100 save book…

Input parameters:

- `args` (string, required): Arguments after `audio`, shell-quoted, absolute paths: "/Users/me/voice.m4a trim normalize podcast save /Users/me/voice.mp3"

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/audiojs-audio/audio#diagnostics

## Score history

- 2026-10-23: 73
- 2026-10-22: 73
- 2026-10-21: 72
- 2026-10-20: 72
- 2026-10-19: 71
- 2026-10-18: 71
- 2026-10-17: 71
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 69
- 2026-10-13: 64
- 2026-10-12: 64
- 2026-10-11: 64
- 2026-10-04: 64
- 2026-10-03: 49

## Common questions

### What is the Audio MCP server?

Audio is an MCP server listed in the public MCP registry as io.github.audiojs/audio. Edit, analyze and convert audio: loudness, spec checks, denoise, EQ, cuts, BPM, key. No ffmpeg. This page covers its npm package (audio).

### Is the Audio MCP server safe to use?

Audio scores 73 out of 100 on VerifyMCP. It declares no install or post-install scripts. 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 Audio MCP server expose?

Audio exposes 1 tool: audio. Their descriptions and schemas cost roughly 745 tokens of context every time the server is loaded.

### Is the Audio MCP server still maintained?

Audio is still listed as active in the MCP registry. We last reached this channel on 23 October 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 Audio MCP server under?

Audio 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

- npm package: https://www.npmjs.com/package/audio
- Socket report: https://socket.dev/npm/package/audio
- Repository: https://github.com/audiojs/audio
- Changelog RSS feed: https://verifymcp.io/servers/audiojs-audio/audio.xml
- Changelog JSON feed: https://verifymcp.io/servers/audiojs-audio/audio.json
- HTML version of this page: https://verifymcp.io/servers/audiojs-audio/audio