diggercamp MCP Server認証済み注目

What is diggercamp?

diggercamp is an AI music-discovery engine for independent music. It finds tracks by how they actually sound — rhythm, timbre, key, energy — not by genre tags, play counts or popularity. The catalogue covers 4M+ independent tracks from Bandcamp, curated YouTube channels and rare-record marketplaces, growing by ~200k tracks a week. No major-label catalogue, no chart noise.

This remote MCP server brings that engine into Claude, ChatGPT, Grok and any MCP-compatible client.

Tools

• find_similar(url) — closest sonic matches to any Bandcamp / YouTube / SoundCloud link
• deep_match(url) — technical match by rhythm, timbre and key; built for DJ sets (Pro/Studio)
• surprise_me(url) — related tracks with wider variety, less obvious picks (Pro/Studio)
• playlist_match(urls) — tracks that fit the combined sound of 2–8 tracks
• inspire_me() — a random track from the crate plus its closest matches
• generate_playlist(url, n, end_url, vibe) — builds and saves a playlist to your diggercamp account, with an energy arc and optional end track

Every result includes links to the source, plus BPM and Camelot key for mixing.

Setup

1. Add the endpoint https://mcp.diggercamp.com/mcp as a custom connector in your client (Claude: Settings → Connectors → Add custom connector; Grok: grok.com/connectors → Custom; ChatGPT: app directory).
2. Sign in with a free diggercamp account when prompted (OAuth).
3. Ask for music that sounds like something you love.

Notes

• Auth: OAuth 2.0/2.1 with PKCE — login happens on diggercamp's own page, the connector only receives a revocable token.
• All tools are read-only except generate_playlist, which writes only to your own account.
• Published on the official MCP Registry as com.diggercamp/music-similarity.
• Docs & FAQ: diggercamp.com/faq · Support: info@diggercamp.com