Sonovault MCP Server

Sonovault MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. MCP server for the SonoVault music metadata API. Search 90M+ tracks, artists, and releases; get genre, label, release dates, ISRC/ISWC codes, and cross-platform IDs.

What you get

MCP server for the SonoVault music metadata API. Gives Claude, Cursor, and any MCP client search across 90M+ tracks, artists, labels, and releases, with full metadata per result: genre, label, release dates, artist credits, ISRC and ISWC codes, and cross-platform IDs (Spotify, Apple Music, Tidal, Beatport, Discogs, MusicBrainz, YouTube).

What the assistant can call

Once Sonovault is connected, these are the calls the assistant has available:

• search_tracks — Fuzzy search by artist + title. Returns ISRC, genre, label, release date
• lookup_isrc — Exact recording lookup by ISRC
• get_track — Fetch a track by SonoVault ID
• get_work_codes — Recording to composition: the ISWC(s) behind a recording
• get_recordings_of_work — Composition to recordings: every recording of an ISWC
• get_platform_links — One track's ID and deep link on all 7 platforms, from any ID or ISRC
• resolve_tracks — Bulk resolve up to 100 track names, ISRCs, or platform IDs
• list_genres — The canonical genre hierarchy
• browse_tracks — Discover by label, artist, genre, or year (paid tier)
• Cursor — Add to ~/.cursor/mcp.json (or .cursor/mcp.json in your project):
• Windsurf — Add the same mcpServers block as Claude Desktop to ~/.codeium/windsurf/mcp_config.json

Configuration and credentials

You will need one environment variable: SONOVAULT_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Setting it up

sonovault-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Sonovault's toolset — search_tracks, lookup_isrc, get_track and 8 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 11 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Sonovault.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the sonovault mcp server does with a few real requests.