Audio MCP vs Notch
A side-by-side look at the Audio MCP and Notch MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
A
Audio MCPMultimedia Process · Local subprocess (stdio)Audio perception for AI agents: measure, see, compare, edit and synthesize sound locally.53GoodAuth: no auth requiredN
NotchMultimedia Process · Remote HTTP/SSETurn product pages and creative briefs into finished video and image ads from your AI chat.45FairAuth: not declaredVerdict: choose Audio MCP for multimedia process work as a local process; choose Notch for multimedia process over a hosted endpoint. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
AChoose Audio MCP when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
AUDIO_MCP_ALLOWED_DIRS, AUDIO_MCP_MAX_SECONDS, AUDIO_MCP_WHISPER_MODEL, AUDIO_MCP_ROOT, AUDIO_MCP_FFMPEG. - You want tools like
audio_analyze, audio_events, audio_view.
NChoose Notch when
- You need dedicated capabilities in the Multimedia Process domain.
- You prefer a remote HTTP/SSE transport.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | A Audio MCP | N Notch |
|---|---|---|
| Category | Multimedia Process | Multimedia Process |
| Quality signal | 53/100 · Good | 45/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Remote HTTP/SSE |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | AUDIO_MCP_ALLOWED_DIRSAUDIO_MCP_MAX_SECONDSAUDIO_MCP_WHISPER_MODELAUDIO_MCP_ROOTAUDIO_MCP_FFMPEG | None listed |
Tools & capabilities
Audio MCP tools 14
audio_analyzePeak, true peak, RMS, LUFS loudness, clipping, DC offset, a loudness sparkline, silence and noise floor, stereo correlation/width/balance, band energy, brightness, tonal vs. noisy, strongest frequencies as note names, pitch, onsets, tempo, edge clicks, loop-seam quality, and an **`issues`** list in…audio_eventsSplits audio into distinct sounds and describes each one: timing, level, attack, tonal/noisy, brightness, pitch or glideaudio_viewPNG waveform and/or spectrogram, with an optional pitch overlay. Every column covers its full time span, so short clicks aren't skipped on long filesaudio_timelineLevel and brightness over time. Streams the file, so it works on recordings of any lengthaudio_melodySingle-line transcription: notes, timings, cents, compact textaudio_transcribeSpeech to text with local Whisper: timed words, language, speaking rate, long pauses and **uncertain words** *(optional extra)*audio_compareA/B summary, metric deltas, per-band dB changes, issues fixed or introduced, and a **null test** (identical? only a gain change? lightly changed?)audio_processAn ordered chain of edits written to a **new** file: gain, peak/LUFS normalize, true-peak limiter, compressor, noise reduction, RMS normalize, trim, fades, crop, pad, high/low-pass, peaking EQ, shelves, DC removal, polarity, mono/stereo, resample, reverse, seamless-loop crossfade, mix, appendaudio_batch_surveyAudits a folder for consistency (loudness outliers, mixed sample rates/channels/formats, uneven leading silence) and returns ready-to-run fixesaudio_batch_processApplies one edit chain to many files and writes them to an output folderaudio_synthesizeDeclarative synth: band-limited oscillators with phase control, noise colours (pink/brown loop seamlessly), sweeps, ADSR, vibrato, tremolo, filters, pan, note sequences, plus exact test signals (impulse, DC, silence)
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Audio MCP
{
"mcpServers": {
"audio-mcp": {
"command": "uvx",
"args": [
"audio-mcp"
],
"env": {
"AUDIO_MCP_ALLOWED_DIRS": "YOUR_AUDIO_MCP_ALLOWED_DIRS_HERE",
"AUDIO_MCP_MAX_SECONDS": "YOUR_AUDIO_MCP_MAX_SECONDS_HERE",
"AUDIO_MCP_WHISPER_MODEL": "YOUR_AUDIO_MCP_WHISPER_MODEL_HERE",
"AUDIO_MCP_ROOT": "YOUR_AUDIO_MCP_ROOT_HERE",
"AUDIO_MCP_FFMPEG": "YOUR_AUDIO_MCP_FFMPEG_HERE"
}
}
}
}
Notch
{
"mcpServers": {
"notch": {
"url": "https://app.usenotch.ai/mcp/setup"
}
}
}
Frequently asked questions
Audio MCP is categorized under Multimedia Process and uses a local stdio subprocess. Notch belongs to Multimedia Process and uses a remote HTTP/SSE transport. Pick Audio MCP for multimedia process work and Notch for multimedia process.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Audio MCP is listed as free. Auth: no auth required. Notch has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add audio-mcp and notch as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Audio MCP has a quality signal of 53/100 (Good) with 0 views, 0 installs and 0 GitHub stars. Notch has 45/100 (Fair) with 26 views, 12 installs and 0 GitHub stars.