tidal_loginLABSCO SUMMARY
Recommendations you get to argue with.
Daily Discovery gives you one aggregate guess and no way to push back. Here you state the constraint — only recent releases, slower, more acoustic — and it is applied against your actual listening history before the playlist is written.
What it is
An MCP server for TIDAL that reads your favourites and playlists, finds similar tracks through TIDAL's API, and writes new playlists back into your account.
What you get
- Your favourite tracks and your playlists read back
- The tracks inside any playlist listed
- Recommendations seeded from a set of tracks plus criteria you state in words
- New playlists created in your TIDAL account
- Playlists deleted
Requirements
Python 3.10 or newer, uv, and a TIDAL subscription. A login step runs against TIDAL before anything else works, and the listening port can be overridden through the environment if the default clashes.
Setup effort
Build from source — git clone https://github.com/yuhuacheng/tidal-mcp.git
USE CASES
01
Building a playlist from your last ten favourites
Read the favourites, ask for similar tracks under your own constraints, and save the result.
02
Getting more of what one playlist already is
List that playlist's tracks and use them as the seed.
03
Narrowing recommendations to a mood or an era
State the criteria in words and the filtering happens before anything is saved.
04
Tidying up playlists you stopped listening to
List what is in the account and delete the ones you name.
05
Connecting the account the first time
The login step authorises against TIDAL before any of the other calls work.
7 tools
Listed in project docs. Your client may show a different list.
get_favorite_tracksrecommend_trackscreate_tidal_playlistget_user_playlistsget_playlist_tracksdelete_tidal_playlistBEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation.
Requires
Python 3.10+
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
Prerequisites: Python 3.10+, uv (Python package manager), TIDAL subscription
TERMINAL
git clone https://github.com/yuhuacheng/tidal-mcp.git
cd tidal-mcp
uv venv
source .venv/bin/activateOn Windows, the activate script is .venv\Scripts\activate instead.
TERMINAL
uv pip install --editable .Open Claude Desktop > Settings > Developer > Edit Config, paste the modified JSON configuration, save, and restart Claude Desktop.
First use: call tidal_login to authenticate through the browser login flow.
MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"TIDAL Integration": {
"command": "<YOUR_PATH_TO_UV>",
"env": {
"TIDAL_MCP_PORT": "5100"
},
"args": [
"run",
"--with",
"requests",
"--with",
"mcp[cli]",
"--with",
"flask",
"--with",
"tidalapi",
"mcp",
"run",
"<YOUR_PATH_TO_PROJECT>/tidal-mcp/mcp_server/server.py"
]
}
}
}
