Audial MCP Server

by audialai Your server? Claim it

local only

Audial MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 1 529 installs a week from pypi. Last commit 30 Oct 2026.

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

Installs per day peak 823 · avg 115 · +53% w/w

a month agotoday

1 529

Installs / week

pypi · audial-mcp

Stars

0 open issues

30 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Audial MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add audial-mcp -- uvx audial-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

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

~/.codex/config.toml

[mcp_servers.audial-mcp]
command = "uvx"
args = ["audial-mcp"]

.cursor/mcp.json

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

.vscode/mcp.json

{
  "servers": {
    "audial-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "audial-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: AUDIAL_USER_ID (Audial user id. Only needed with an older API key that does not start with aud_), AUDIAL_API_KEY (Audial API key, for servers and CI. Leave unset to sign in through the browser on first use), AUDIAL_RESULTS_DIR (Folder results are written to), AUDIAL_JOB_TIMEOUT_S (Seconds to wait for a job before giving up), AUDIAL_API_BASE_URL (Override the Audial API base URL (advanced)).

Alternatives to Audial MCP

same job, measured the same way

Vocuno

by vocuno

AI music studio: song generation with vocals, covers, stems, voice conversion, mastering, editing.

answering

Audiolla

by psyb0t

Self-hosted MCP server: audio stems, mastering, MIR analysis, DSP, MIDI, speech tools.

local only

Testing

by rog0x

Test generation, mocks, coverage analysis for AI agents

33 installs/wk local only

Medux

by meduxio

AI video, image, speech, voice cloning and avatar generation, plus PDF/audio/video editing tools.

answering

Tag-per-Track

by lory97

Audio analysis and A&R scoring for music tracks: tags, lyrics, artist stats, demo triage.

75 installs/wk local only

Aetherwave MCP

by aetherwave-studio

Music, image, video and audio generation across top AI providers - one key, one credit pool.

100 installs/wk local only

Audio Sonic MCP

by ripunjay-kashyap

Local-first audio analysis: BPM, musical key, production profile, and CLAP vibe embeddings.

local only

Cartelera

by cartelera

AI video and music studio: music videos, ads, voiceovers and audio analysis (genre, BPM, key).

answering

Audial MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Audial MCP?

Audial MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package audial-mcp was installed 1 529 times last week.

How do I connect Audial MCP?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls audial-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Audial MCP?

The pypi package audial-mcp was installed 1 529 times in the last week. Week over week that is +53%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Audial MCP open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.