MCP.so
Sign In

diggercamp MCP ServerVerifiedFeatured

@Tommaso Savorana (ti es)

Basic information

Transport

Streamable HTTP

Authentication

OAuth

Category

Media & Design

Author

Tommaso Savorana (ti es)

Submitted by

Tommaso

About diggercamp MCP Server

diggercamp finds independent music by how it sounds. Paste any Bandcamp, YouTube or SoundCloud link and get the closest sonic matches from 4M+ independent tracks — matched by rhythm, timbre, key and energy, not genre tags or popularity. 6 tools: find_similar, deep_match, surprise_me, playlist_match, inspire_me, generate_playlist. Works in Claude, ChatGPT and Grok.

#music#audio#discovery#similarity#dj#bandcamp#playlists#independent-music

Connection details

https://mcp.diggercamp.com/mcp

Setup

claude mcp add diggercamp --transport http https://mcp.diggercamp.com/mcp

diggercamp MCP Server tools

6

Find sonically similar tracks to a song (closest by sound). Paste a Bandcamp, YouTube or SoundCloud link.

Deep Match: technical match by rhythm, timbre and key — great for building DJ sets. Requires a Pro or Studio plan.

Surprise: sonically related tracks with wider variety / less obvious picks. Requires a Pro or Studio plan.

Find tracks that fit a SET of 2-8 tracks together (their combined sound / centroid), not similarity to a single seed. Pass 2-8 Bandcamp/YouTube/SoundCloud links.

Discovery: pick a starting track and show similar tracks. For signed-in users with search history the pick is personalised on their recent digs; spread controls how far to roam: familiar (right next to their digs), fresh (close relatives, default), adventurous (two hops out, same lineage but unexpected), random (the whole crate).

Generate and SAVE a playlist to the user's diggercamp account. It starts from a seed track and develops the set from there (energy and genre flow), optionally ending on a chosen track. Requires the user to be signed in to diggercamp. - url: seed track link (Bandcamp / YouTube / SoundCloud) — the playlist starts here. - n: number of tracks, 5 to 30 (default 15). - end_url: optional link of the track to END on. - vibe: optional one of warm_up, afterhours, yoga, focus, sunset (shapes the energy curve).

Overview

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

Frequently asked questions

1

What is the diggercamp remote MCP server?

The diggercamp remote MCP server is a hosted Model Context Protocol endpoint at https://mcp.diggercamp.com/mcp, so AI assistants can connect to it without installing or running anything locally.

2

How do I connect to the diggercamp MCP server?

Add the endpoint https://mcp.diggercamp.com/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.

3

Does the diggercamp MCP server require authentication?

Yes. diggercamp uses OAuth: the first time you connect, your MCP client opens a browser window to sign in and authorize access, then reuses the credentials for future sessions.

4

Which transport does the diggercamp MCP server use?

diggercamp exposes a Streamable HTTP endpoint, the transport used by remote MCP servers and supported by all major MCP clients.

Comments