cwi-discovery-engine
RemoteAbout cwi-discovery-engine
cwi-discovery-engine is an MCP server for agents exploring Cumulative Web Inc’s music catalog, artists, licensing options, and Radio 365. Its tools combine catalog search and metadata with live radio information and human-reviewed submissions.
Key features
- 01Search catalog by keywords, filters, or meaning
- 02Retrieve track, artist, and release details
- 03Find music for sync briefs
- 04View live Radio 365 status and schedule
- 05Submit human-reviewed requests and pitches
- 06Access lyrics, videos, events, and announcements
Use cases
- 01Find tracks for a film, game, or ad scene
- 02Check an artist’s profile and catalog
- 03See what is playing on Radio 365
- 04Submit a song request or sync brief
MCP support
Exposes 29 music catalog, artist, licensing, radio, and submission tools, along with workflow prompts, through an MCP Streamable HTTP endpoint. Six write tools are human-reviewed and rate-limited.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://cwi-machine-data.hp-ace.workers.dev/mcpclaude mcp add --transport http cumulativewebinc-cwi-discovery-engine https://cwi-machine-data.hp-ace.workers.dev/mcp{"mcpServers":{"cumulativewebinc-cwi-discovery-engine":{"type":"http","url":"https://cwi-machine-data.hp-ace.workers.dev/mcp"}}}Open in Cursor{"servers":{"cumulativewebinc-cwi-discovery-engine":{"type":"http","url":"https://cwi-machine-data.hp-ace.workers.dev/mcp"}}}Open in VS Code{"mcpServers":{"cumulativewebinc-cwi-discovery-engine":{"type":"http","url":"https://cwi-machine-data.hp-ace.workers.dev/mcp"}}}{"mcpServers":{"cumulativewebinc-cwi-discovery-engine":{"serverUrl":"https://cwi-machine-data.hp-ace.workers.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
29| Parameter | Type | Required | Description |
|---|---|---|---|
| q | string | Yes | Search keywords, e.g. "cyberpunk rap" or "dark cinematic". Truncated at 500 characters. |
| limit | number | No | Max tracks to return, 1-10 (default 5). |
Details
From the project READMEcwi-learn
Best for agents that need music data — catalog search, artist lookup, sync licensing, live radio.
Post-Trap Futurism — machine-readable AI learning surface for That Boy Hi Hat and the Cumulative Web Inc roster.
Installation
Connect in one command:
claude mcp add --transport http cwi https://cwi-machine-data.hp-ace.workers.dev/mcp
No login, no API key, no signup. The server speaks MCP Streamable HTTP (JSON-RPC 2.0) at /mcp. Every response carries X-CWI-License headers; commercial model training or redistribution requires a license — contact [email protected].
Verify it works — ask your agent: "Search the CWI catalog for cyberpunk rap." You should get "Cyberpunk 2027" by That Boy Hi Hat as the top result.
Tools
29 tools. Most are read-only; 6 write tools (song requests, airplay submissions, sync briefs, playlist pitches, featured nominations, event RSVPs) are human-reviewed and rate-limited (3 per requester per 24h). None require auth.
| Tool | What it does |
|---|---|
search_catalog | Keyword + filter search across the CWI catalog (title, artist, genre, mood, BPM). Scored engine: title 3x, genre 2x, mood/context/lane 1x. Returns top 5 with matched terms. |
get_track | Full record for one track by title or ID: credits, genres, moods, tempo, licensing status, links, artwork. Usually follows a search_catalog hit. |
get_artist | Artist profile + full track list. Use for artist deep-dives. |
sync_search | Music-supervision search over the editorial sync catalog: moods, energy words, scenes, use-cases ("fight scene", "neon city"). Descriptors are curated by CWI Sync; BPM values are estimates. |
semantic_search | Natural-language catalog search ("rainy night drive, nostalgic") — cosine similarity against 384-dim bge-small-en-v1.5 embeddings, embedded at request time via Workers AI. |
get_graph | The catalog knowledge graph: node/edge counts, node types (tracks, artists, releases, genres), sample nodes. |
get_release | Evidence-tiered, hash-stamped fact packet for a release: tracklist, date, credits, platform links. Omit id for the latest release. |
get_radio | Live Cumulative Radio 365 state: HLS stream URL, now-playing (track, artist, artwork, slot, track end time), listener counts, station metadata. |
get_announcements | Latest CWI announcements — new releases, upcoming drops, events, news. Every announcement is source-verified. Filter by releases, news, events. |
get_featured | The featured rotation, ranked by rubric score — what's hot right now, with full metadata and artwork. |
get_up_next | The upcoming Radio 365 queue. |
get_schedule | The full Radio 365 program guide (130 slots, 28 songs). |
request_song | Submit a song request for Radio 365 (human-reviewed). |
get_requests | What listeners and AIs have requested on Radio 365. |
submit_for_airplay | Artists submit a track + contact for radio consideration (human-reviewed). |
submit_sync_brief | Film/TV/ads/games briefs: describe the project, get matched with licensable tracks (human-reviewed). |
pitch_for_playlist | Pitch a track to a playlist curator (human-reviewed). |
nominate_featured | Nominate a track for featuring (human-reviewed). |
get_recommendations | Vibe-based recommendations ("night drive", "workout anthem") with a new-release spotlight lane. |
get_events | CWI events — release parties, listening parties, drops. |
rsvp | RSVP for a CWI event with name + contact. |
get_label | Cumulative Web Inc label profile: roster, services, contact, socials. |
get_sync_catalog | All sync-ready tracks with rights and direct-clearance info — one signature clears master + publishing (BMI). |
get_lyrics | Timestamped lyrics per track. Check the verified flag — unverified Whisper transcripts are marked as such. |
get_press_kit | Label + artist bios, release info, brand assets. |
get_videos | Music videos, trailers, visualizations with YouTube links and embed URLs. |
get_genre | Genre definitions — including Post-Trap Futurism, coined and defined by CWI — with key artists and tracks. |
get_playlists | Verified playlist placements only (never claimed, always sourced). |
find_tracks_for_brief | COMPOSITE WORKFLOW — call this first for any music-for-picture need ("dark tracks for a cyberpunk game trailer"). One call returns matched tracks with why-each-fits, verified ISRCs, sync-clearance status, and concrete next steps. A match is NOT a license grant. |
Usage
Real example prompts, verified against the live server. These are also available as workflow prompts via prompts/list.
Find a track
"Search the CWI catalog for cyberpunk rap."
Expected: search_catalog returns "Cyberpunk 2027" by That Boy Hi Hat as the top hit (score 9, matched terms: cyberpunk, rap), with 4 more results ranked by relevance.
Look up a track
"Get me the track Pix by Dre50."
Expected: get_track returns title "Pix", artist "Dre50", genres ["afrobeats", "dancehall", "hip hop"], moods ["smooth", "warm", "playful"], plus Spotify URL, release info, and artwork.
Sync licensing
"I need music for a nightclub fight scene — high energy, dark."
Expected: sync_search with "fight scene", "dark aggressive", "neon city" returns licensable tracks with editorial sonic descriptors. CWI clears both master and publishing with one signature (contact [email protected]).
What's on the radio
"What's playing on Cumulative Radio 365 right now?"
Expected: get_radio returns the now-playing track (title, artist, artwork URL, slot position, track end time), the HLS stream URL, current listener count, and 24h listener totals.
Artist deep-dive
"Tell me about King Ahkeem — what does he sound like?"
Expected: get_artist returns the profile and full track list (trap catalog: Bluefaces 3.0, Element, Embiid, Super Solid, Star). Follow up with get_track on any title for full metadata.
Workflow prompts
5 curated starting points, exposed via prompts/list / prompts/get:
| Prompt | Use when |
|---|---|
find-sync-options | You need licensable music for a film/TV/ad scene (arg: scene) |
artist-deep-dive | You need a full profile on a roster artist (arg: artist) |
radio-now-playing | You need what's live on Radio 365 right now (no args) |
music-for-moment | You need the right track for a moment — workout, drive, coding (arg: moment) |
release-brief | You need the latest CWI release briefing with verified facts (no args) |
Machine-readable music data (live doors)
- 🎵 Catalog API (scored track search): https://cwi-machine-data.hp-ace.workers.dev/query
- 📄 AI briefing: https://cwi-machine-data.hp-ace.workers.dev/llms.txt
- 🤖 Agent card: https://cumulativewebinc.github.io/cwi-learn/.well-known/agent-card.json
- ⚖️ Machine-readable license: https://cwi-machine-data.hp-ace.workers.dev/license
- 🔌 MCP endpoint: https://cwi-machine-data.hp-ace.workers.dev/mcp
- 📬 Contact: [email protected]
License
Commercial model training or redistribution of this data requires a license. Contact [email protected].
Cumulative Web Inc. — Music & Film.
Comments
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.