Skip to main content
Glama
@audiolabtools/mcp-server

@audiolabtools/mcp-server

@audiolabtools/mcp-server

Listed on mcpservers.org

MCP (Model Context Protocol) server that gives any MCP-capable AI (Claude Desktop, Claude Code, Cursor, and others) ten audio-analysis tools, backed by the hosted AudioLab API. It is a thin HTTP client: no local audio engine, no ffmpeg, nothing to compile. It can measure a public URL or a local file on your machine, but the measuring always happens on the hosted API: the file is read here and uploaded there (see Privacy).

Install

Point your MCP client at the package via npx (nothing to install globally). No account needed for a first score:

{
  "mcpServers": {
    "audiolab": {
      "command": "npx",
      "args": ["-y", "@audiolabtools/mcp-server"]
    }
  }
}

Without a key you are on the keyless trial: 20 calls a month and 3 a minute per IP address, for single analyses of a URL or a local file up to 4 MB. Batches and larger files need a key. A free key gives 1,000 calls and 2 GB a month, no card: sign in at https://audiolab.tools/account, generate one, and add it:

"env": { "AUDIOLAB_API_KEY": "al_live_yourkey" }

Related MCP server: Audio Analysis MCP Server

Requirements

  • Node ≥ 18: uses the built-in global fetch + AbortSignal.timeout.

  • Optionally an AUDIOLAB_API_KEY (see Install). No ffmpeg, no native dependencies.

Tools

Every tool takes one audio source: a public url or a local path:

  • { url: "https://…" }: a public https URL the API fetches server-side.

  • { path: "./mix.wav" }: a file on the machine running this server. Files up to 4 MB are sent inline; larger files (up to 150 MB) upload over a signed URL, are analysed, and are swept from storage within the hour. (Local path works only in this stdio server, not the remote /mcp endpoint.)

Tool

Returns

analyze_loudness

Integrated LUFS (EBU R128 / BS.1770-4), true-peak (dBTP), LRA, crest factor, stereo correlation, mono compatibility, tonal balance

check_target

Pass/fail vs a delivery target (spotify / apple-music / youtube / tidal / amazon-music / podcast / ebu-broadcast / atsc-broadcast, or target:"custom" + lufs+tp), with per-metric deltas; passes within ±0.5 LU of the target with true peak at most 0.5 dB above it. On a fail it adds a single-pass ffmpeg loudnorm command as a starting point: measure the output again, single-pass can miss the margin

analyze_timeseries

Short-term LUFS over time + downsampled waveform peaks (waveformPoints?)

get_spectrum

FFT magnitude data + 7-band energies

analyze_voice

Voice QA: speech/silence ratio, speaking rate, SNR, noise floor, pause energy, sibilance & clipping risk

get_speech_segments

Voiced regions with start/end + per-segment RMS (auto-trim, chapters)

index_signal

Content-type guess, tags, clipping/silence regions, brightness & dynamics buckets. Add bandLimit:true for bandLimit.upsampled: yes, no or cannot-say, with the reason in plain words (guide: https://audiolab.tools/docs/start/is-my-audio-upsampled)

analyze_profile

One named question, voice, master, provenance, dataset, environment, broadcast, loop, room (reverberation from a clap, a pop, an impulse response or a sweep; pass roomSource), chain (lost packets) or pitch (where a voice sits and how clean it is), answered with only the lenses it needs. These ten need a paid plan; the free tier gets the basic profile, keyed by stable lens id. Add series:true for the curves, per-block lanes and per-phrase values. Add liveEvents:true for liveEvents: the file read as a stream by the live monitor of /live, with every gap, clipping, level drop, dead air and hum it raised, all with status signals. Carries a note when the profile’s voice lenses land on non-speech material. Full catalogue: https://audiolab.tools/lenses

compare_loudness

A/B on two sources (urlA/pathA + urlB/pathB), returns both results

analyze_batch

One route over up to 20 sources in a single call (urls and/or paths), per-item ok/data/error. For folder QA, library indexing, or checking a whole release against a target; with endpoint:"signallab/index" it takes bandLimit:true too. Each item meters as one call

Example asks to your AI:

  • “Analyze the loudness of https://example.com/track.wav” → analyze_loudness with url

  • “Is this take usable?” → analyze_profile with profile:"voice"

  • “Has this file been re-encoded, and is it all one source?” → analyze_profile with profile:"provenance"

  • “Which of these recordings were upsampled?” → analyze_batch with endpoint:"signallab/index" and bandLimit:true

  • “Run loudness on ./master.wav” → analyze_loudness with path

  • “Does ./mix.mp3 pass Spotify?” → check_target with path + target:"spotify"

Configuration (env)

Var

Default

Purpose

AUDIOLAB_API_KEY

– (optional)

Your API key. Without it: the keyless trial (20 calls a month per IP, no batches, files up to 4 MB).

AUDIOLAB_API_BASE

https://audiolab.tools/v1

Override the API base (must be https://).

AUDIOLAB_TIMEOUT_MS

330000

Per-request timeout in milliseconds (long files and batches stream server-side and can legitimately take minutes).

Privacy

Analysis happens on the AudioLab API, so the audio does reach audiolab.tools: a url is fetched server-side, and a local path is read here and uploaded to the API (small files in the request body; larger files via a private one-shot signed upload into EU storage). The API returns numbers only and does not keep your audio: a direct request is decoded and discarded inside the request, and a signed upload is swept from storage within the hour (see https://audiolab.tools/privacy). This package has no telemetry and writes nothing to disk. There is no offline mode, and the engine is not published as an installable package. If audio must never leave the machine, don't use a hosted analyser; the in-browser labs on the website measure on-device, but they are for people, not for agents.

Limits

  • Local files: up to 150 MB (host bigger ones at a public URL).

  • Duration: loudness routes (analyze_loudness, check_target, analyze_timeseries, get_spectrum) handle long files (podcast episodes, full sets, up to ~3 h) via server-side streaming; voice/signal routes are limited to ~7 minutes.

  • One file per call (agents loop for many); one-shot (no streaming/realtime).

  • Rate and monthly limits are enforced by the API, per key (per IP address on the keyless trial).

Smoke test

node hosted-server.mjs --selftest   # verifies the 10 tools + guards; no network

License

MIT © Nathan Renting

Available Tools

10 tools
analyze_batchBatch: one analysis route over many filesA

Run one analysis route over up to 20 audio sources in a single call. Returns per-item ok/data/error; each item is metered as one call. Routes: mixlab/analyze (default), mixlab/check-target, mixlab/timeseries, mixlab/spectrum, voicelab/qa, voicelab/segments, signallab/index. Use for folder QA, library indexing, or checking a whole release against a loudness target. Sources: public https urls and/or local file paths.

Inputs: tp, lufs, urls, paths, +2 more.

analyze_loudnessAnalyze loudness (MixLab)B

Loudness and dynamics for a track: integrated LUFS (EBU R128 / BS.1770-4), true-peak (dBTP), loudness range (LRA), crest factor, stereo correlation, mono compatibility, and tonal balance. Audio source: a public https URL, or a local file path (path).

Inputs: url, path.

analyze_profileAnalyse against a profileA

Measure a file against a named working set of lenses and get back only what that question needs. Profiles: voice (is this take usable, and which phrase is the problem), master (will this translate to real platforms and speakers), provenance (what has been done to this file, and is it all one source), dataset (which of these files are good enough, and why not the rest), environment (what is in this space, and what kind of noise is it), broadcast (does this file meet the delivery spec), loop (is this loop clean, on the grid, and safe to drop in a DAW). basic is the free tier; the other seven need a paid plan. Results are keyed by stable lens id. Only the analysis passes the profile needs are run. Set series:true to also get the curves, the per-block lanes and the per-phrase values,a much larger payload, so leave it off unless you are going to read them. Audio source: a public https URL, or a local file path (path).

Inputs: profile (required), url, path, series.

analyze_timeseriesLoudness over time (for graphing / visualization)B

Short-term LUFS samples over time (EBU R128, ~3s window) with their time-base, plus downsampled waveform peaks. Arrays suitable for loudness-over-time charts, level meters, and waveform UIs. Audio source: a public https URL, or a local file path (path).

Inputs: url, path, waveformPoints.

analyze_voiceAnalyze voice quality (VoiceLab)A

Speech-quality QA for a voice recording: speech/silence ratio, speaking-rate label, signal-to-noise, noise floor, pause energy, sibilance risk, clipping severity. Gates a voice take. Audio source: a public https URL, or a local file path (path).

Inputs: url, path.

check_targetCheck audio against a loudness target (Spotify, EBU, etc.)A

Verify whether audio hits a delivery target (Spotify -14 LUFS / EBU broadcast -23 / podcast -16 / etc.). Returns pass/fail with per-metric deltas and a concrete ffmpeg loudnorm command to fix if failing. Presets: spotify, apple-music, youtube, tidal, amazon-music, podcast, ebu-broadcast, atsc-broadcast; or target="custom" with lufs+tp. Audio source: a public https URL, or a local file path (path).

Inputs: target (required), tp, url, lufs, +1 more.

compare_loudnessCompare two tracks (A/B)A

Run loudness analysis on TWO sources and return both results for an A/B comparison: master vs reference, before vs after a fix, two encoders, two cuts. Audio source: a public https URL, or a local file path (path).

Inputs: urlA, urlB, pathA, pathB.

get_spectrumFFT spectrum dataA

Frequency-domain magnitude data (paired frequency/magnitude arrays) plus energies in 7 standard bands (sub/bass/lowMid/mid/highMid/presence/air). There is no dominant-band field in the response. For spectrum-analyzer UIs and tonal-balance analysis. Audio source: a public https URL, or a local file path (path).

Inputs: url, path.

get_speech_segmentsSpeech segments (VoiceLab)A

List voiced speech regions with start/end timestamps and per-segment RMS. For auto-trim, chapter generation, and speaker-turn detection. RMS-based voice-activity detection, not speaker diarization. Audio source: a public https URL, or a local file path (path).

Inputs: url, path.

index_signalIndex a signal (SignalLab)A

A metadata index for any audio file: content-type guess (voice/music/mixed/noise/silence) with confidence, brightness & dynamics buckets, dominant band, clipping/silence regions, and tag suggestions. For triage or auto-tagging a library. Audio source: a public https URL, or a local file path (path).

Inputs: url, path.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools target a distinct analysis lens (loudness, spectrum, voice, segments, index), but analyze_profile is an umbrella that overlaps with analyze_voice, analyze_loudness, and index_signal, and analyze_timeseries sits close to analyze_loudness. Descriptions largely disambiguate by scoping each to a specific output, so confusion is limited to a couple of pairs.

    Naming Consistency5/5

    All ten tools follow a consistent snake_case verb_noun pattern (analyze_loudness, check_target, get_spectrum, compare_loudness, index_signal, analyze_batch). No mixed conventions or stylistic outliers.

    Tool Count5/5

    Ten tools is well within the sweet spot and each earns its place: distinct analysis lenses, a target checker, a comparator, and a batch runner. Nothing feels redundant or thin.

    Completeness4/5

    The surface covers the core audio-QA lifecycle: measurement (loudness, spectrum, timeseries), voice QA, indexing, target verification, comparison, and batch runs. Minor gaps like no dedicated silence/clipping-region extractor or format/provenance-specific operation are largely absorbed by analyze_profile and index_signal.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to analyze audio files, extracting tempo, key, beat drops, volume surges, high tones, loudness, brightness, and structure, and returning structured JSON and visualizations.
      2
      MIT