Digcrate’s agent queries across 20+ specialized data sources in a single research session. These integrations are provided by the crate-cli npm package — Digcrate imports MCP tool servers from crate-cli rather than implementing them directly.
Each tool server exposes a set of MCP-compatible tools. The agent selects which tools to call based on the query, then executes them in sequence or parallel as needed.
Music databases
These are the core sources for music metadata, credits, samples, and discovery.
| Source | Data provided |
|---|
| Discogs | Releases, labels, master recordings, credits, cover art, vinyl pressings, marketplace data |
| MusicBrainz | Artist metadata, relationships, recordings, release groups, work credits |
| Last.fm | Similar artists, genre tags, listener counts, top tracks, listening stats |
| Genius | Lyrics, annotations, song metadata, writer and producer credits |
| WhoSampled | Sample origins, interpolations, covers, and remixes |
| Bandcamp | Album search, tag exploration, related tags, artist pages |
EMBEDDED_DISCOGS_KEY + EMBEDDED_DISCOGS_SECRET) and Last.fm (EMBEDDED_LASTFM_KEY) need keys set in your environment. MusicBrainz, Genius, WhoSampled, and Bandcamp are accessed without authentication.
General knowledge
| Source | Data provided |
|---|
| Wikipedia | Artist biographies, discography context, genre history, label histories |
Events
| Source | Data provided |
|---|
| Ticketmaster | Concert listings, ticket availability, venue details, event dates |
EMBEDDED_TICKETMASTER_KEY in your environment. Get a key at developer.ticketmaster.com.
Connected (via Auth0 Token Vault)
These sources require the user to connect their account through Settings. The connection is managed by Auth0 Token Vault — Digcrate never stores raw OAuth tokens.
| Source | Data provided |
|---|
| Spotify | User library, saved albums, followed artists, playlists, top artists, top tracks. Create and export playlists. |
Spotify integration requires Auth0 Token Vault to be configured (AUTH0_DOMAIN, AUTH0_CLIENT_ID, AUTH0_CLIENT_SECRET). See Environment variables and Deployment for setup instructions.
| Source | Data provided |
|---|
| fanart.tv | High-resolution artist backgrounds, logos, album art, thumbnails |
| iTunes | Album artwork, track search, artist lookup |
| YouTube | Music videos, documentaries, live performances, interviews |
Web research
These sources extend the agent beyond structured databases into open-web research with citations.
| Source | Data provided |
|---|
| Exa.ai | Semantic web search — finds conceptually relevant articles, reviews, and blog posts |
| Tavily | AI-optimized web search with structured result extraction |
| Perplexity (Sonar) | Research enrichment with inline citations. Used for influence mapping pull quotes and show prep context. |
Exa, Tavily, and Perplexity each require their own API keys, which users configure in the Settings → API Keys panel within the app. These keys are stored encrypted in Convex and sent to the agent at runtime. They are not set as server-side environment variables.
Memory
| Source | Data provided |
|---|
| Mem0 | Cross-session user memory. The agent can remember preferences, saved artists, and research context across sessions. |
Mem0 is available on the Pro plan. Users configure their Mem0 API key in Settings → API Keys.
Radio
| Source | Data provided |
|---|
| Radio Browser | 30,000+ live radio stations searchable by genre, country, name, or tag. Streams directly in the workspace audio player. |
When a user sends a query, the agent receives the full list of available tools from all MCP servers. It decides which tools to call based on the query content and the system prompt. The agentic loop executes tool calls sequentially, feeding results back to the model until it has enough information to write a final answer.
For research-heavy commands (e.g. /influence, /story, /track), the agent gets a higher tool-call cap to allow deeper multi-source lookups. For conversational queries, it may use only one or two tools or none at all.
The tool execution log for each session is visible in the chat panel as collapsible “thinking” steps, showing which sources were queried and how long each call took. 