mcpField
T
Tunetank Mcp

Tunetank Mcp

Local
github.com/tunetankMedia & Design8Updated 16w ago

About Tunetank Mcp

Tunetank MCP exposes Tunetank’s music and sound-effects catalog to AI assistants. Creators can search tracks and SFX and receive preview and catalog links; downloads and licensing remain on Tunetank.

Key features

  1. 01Search music by metadata and duration
  2. 02Search SFX by category and duration
  3. 03Browse genres, moods, themes, and playlists
  4. 04Return audio previews and track pages

Use cases

  1. 01Find a timed music track for a video intro
  2. 02Locate a short whoosh effect for a clip

MCP support

The server provides MCP tools for searching music and SFX and browsing catalog categories and playlists. Results include preview URLs and canonical track pages.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"tunetank": {
"command": "npx",
"args": [
"-y",
"mcp-remote"
]
}
}
}
Run commandnpx -y mcp-remote

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-remote

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Tunetank MCP Server

The Tunetank music & sound‑effects catalog as an MCP server — so any AI assistant (Claude, ChatGPT, Cursor, …) can find the right royalty‑free track or SFX for a video, ad, podcast or stream.

Ask things like “find an energetic rock track around 60 seconds for a YouTube intro” or “a whoosh SFX under 2 seconds” and the assistant searches Tunetank's real catalog and hands back a preview link plus the track page on tunetank.com.

  • 🎵 Search music by mood, genre, theme, artist, name and target length (± tolerance)
  • 🔊 Search sound effects (SFX) by category and length
  • 📚 Browse genres, moods, themes and curated playlists
  • ▶️ Every result includes an audio preview URL and the canonical track page (https://tunetank.com/track/<id>-<slug>/)
  • 🆓 Completely free — no API key, no auth, no rate‑limit sign‑up. Read‑only.

Server

Endpointhttps://mcp.tunetank.com
TransportStreamable HTTP (JSON‑RPC 2.0)
AuthNone (public, read‑only)
CostFree

Setup

Point any MCP‑capable client at the endpoint above. Examples for common clients:

Claude Desktop / Claude.ai (Connectors)

Add a Custom Connector with the URL:

https://mcp.tunetank.com

Or, via the config file (claude_desktop_config.json) using the mcp-remote bridge:

{
  "mcpServers": {
    "tunetank": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.tunetank.com"]
    }
  }
}
Cursor

~/.cursor/mcp.json:

{
  "mcpServers": {
    "tunetank": {
      "url": "https://mcp.tunetank.com"
    }
  }
}
VS Code / other clients

Any client that supports remote (HTTP) MCP servers — just use the URL https://mcp.tunetank.com. For clients that only speak stdio, bridge with npx -y mcp-remote https://mcp.tunetank.com.


Tools

ToolArgumentsReturns
search_musicquery, name, artist, genre, mood, theme, duration, tolerance, limitTracks: name, artist, duration, bpm, preview URL, track page URL, genres/moods/themes
search_sfxquery, category, duration, tolerance, limitSound effects: name, duration, preview URL, waveform
list_genres—All music genres (id, name, alias)
list_moods—All music moods (id, name, alias)
list_themes—All music themes (id, name, alias)
list_playlistslimitCurated playlists (name, description, track count)
Argument notes
  • query (search_music) — free text; matches the track name or the artist name.
  • genre / mood / theme — accept either a name/alias (e.g. "rock", "happy") or a numeric id (from the list_* tools).
  • duration — target length in seconds.
  • tolerance — allowed ± seconds around duration (default 5). Example: duration: 60, tolerance: 10 → tracks between 50s and 70s.
  • category (search_sfx) — SFX category name or id.
  • limit — max results (default 20, max 50; playlists default 50, max 200).

All string filters are partial, case‑insensitive matches. Only published tracks/SFX are returned.


Examples

“Energetic rock, ~60s, for an intro”

{
  "name": "search_music",
  "arguments": { "genre": "rock", "mood": "energetic", "duration": 60, "tolerance": 10, "limit": 5 }
}

“A short whoosh sound effect under 2 seconds”

{
  "name": "search_sfx",
  "arguments": { "query": "whoosh", "duration": 1.5, "tolerance": 1.5 }
}

Sample track result

{
  "id": 2270,
  "name": "Adventures",
  "artist": "A Himitsu",
  "duration": 138,
  "bpm": 120,
  "url": "https://tunetank.com/track/2270-adventures/",
  "preview": "https://…/preview.mp3",
  "genres": ["Pop"],
  "moods": ["Happy", "Inspiring"],
  "themes": ["Vlog"]
}

Try it (raw JSON‑RPC)

The transport is spec‑strict, so include both Content-Type and Accept headers:

# List available tools
curl -s https://mcp.tunetank.com \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

# Search music
curl -s https://mcp.tunetank.com \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"search_music","arguments":{"mood":"happy","duration":60,"tolerance":10,"limit":3}}}'

Licensing

All music is free to use for personal and non‑commercial purposes.

For anything else (commercial projects, ads, monetized content, client work, etc.), head to tunetank.com and review the licensing terms there.


About

Music and sound effects come from Tunetank — royalty‑free audio for creators. This MCP server is a discovery channel: it returns previews and track pages so you can listen and grab the track on tunetank.com. Downloading and licensing happen on the site.

Questions or issues? Reach out at [email protected].

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.