Skip to main content

Internet radio MCP server — search and play 30,000+ stations via AI

Project description

radiomcp

MCP server for internet radio - search and play 55,000+ stations from 200+ countries.

Powered by Airtune API.

Installation

pip install radiomcp

Player (choose one)

Player macOS Linux Windows
mpv (recommended) brew install mpv apt install mpv winget install mpv
VLC brew install vlc apt install vlc vlc.io
ffplay brew install ffmpeg apt install ffmpeg ffmpeg.org
browser No install needed No install needed No install needed

Auto-detection: mpv > vlc > ffplay > browser

Claude Desktop Setup

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "radio": {
      "command": "python3",
      "args": ["-m", "radiomcp"]
    }
  }
}

Restart Claude Desktop.

Usage

Just ask Claude naturally:

  • "Play some jazz radio"
  • "Find Korean news stations"
  • "What song is playing?"
  • "I want relaxing music"
  • "Set sleep timer for 30 minutes"
  • "Wake me up at 7am with jazz"
  • "Stop the radio"

Features

  • 51,000+ stations from 200+ countries
  • Fast search (~5ms local DB)
  • Multilingual (50+ languages: Korean, Japanese, Chinese, Russian, etc.)
  • Korean broadcasters (KBS, MBC, YTN - auto token refresh)
  • AI recommendations (mood, time, weather, personalized)
  • Song recognition (stream metadata + Whisper)
  • Sleep timer & alarm
  • Favorites & history
  • Volume control (mpv)
  • Auto URL refresh (handles token expiration)
  • Remote blocklist (GitHub-based updates)
  • Daily updates (new stations synced automatically)

Tools

Playback

Tool Description
play Start playback
stop Stop playback
resume Resume last station
now_playing Current song info
set_volume / get_volume Volume control

Search

Tool Description
search Search by keyword
search_by_country Search by country code
advanced_search Combined filters
get_popular Popular stations

Recommendations

Tool Description
recommend Mood-based (relaxing, energetic, focus)
recommend_by_weather Weather-based
recommend_by_time Time of day based
personalized_recommend Based on history
similar_stations Find similar

Timer

Tool Description
set_sleep_timer Auto-stop after N minutes
set_alarm Wake-up alarm

Favorites

Tool Description
get_favorites List favorites
add_favorite Add to favorites
play_favorite Play from favorites

More

Tool Description
recognize_song Song recognition
get_history Listening history
get_user_profile Taste analysis
get_radio_guide Full guide for AI

See HELP.md for complete documentation.

Requirements

  • Python 3.10+
  • Audio player (mpv recommended)

Data Sources

License

Disclaimer

See DISCLAIMER.md for terms of use.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

radiomcp-1.0.2.tar.gz (117.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

radiomcp-1.0.2-py3-none-any.whl (121.4 kB view details)

Uploaded Python 3

File details

Details for the file radiomcp-1.0.2.tar.gz.

File metadata

  • Download URL: radiomcp-1.0.2.tar.gz
  • Upload date:
  • Size: 117.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for radiomcp-1.0.2.tar.gz
Algorithm Hash digest
SHA256 77d6876fed698713590d5111c8e5fa8d065a2b976237b926c0b9f32c63b4857b
MD5 768ad512c8890662039110be37237217
BLAKE2b-256 179ba639577e56f234284dd75aedc4f4d50e45bde2e85b8a7c5f6e3f9cf5d844

See more details on using hashes here.

File details

Details for the file radiomcp-1.0.2-py3-none-any.whl.

File metadata

  • Download URL: radiomcp-1.0.2-py3-none-any.whl
  • Upload date:
  • Size: 121.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for radiomcp-1.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 7869e9a047ad9e60980a7f5c8aa7c0cbaaeecd76a746af0b1d8143e8e35cfa37
MD5 8593581c14d88e22d29e6d3505612422
BLAKE2b-256 aa02668adf9b493dccb174235420f3a8ffcad37bd50e5826bcf2f993e7328d10

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page