프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. 리뷰와 계정 기능은 다음 단계에서 열려요.
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

Cwi Discovery Engine

제작자: CumulativeWebInc버전 1.3.0i★ –i클라우드에서 실행
레지스트리 이름io.github.CumulativeWebInc/cwi-discovery-engine

설치

개요

제작자가 쓴 설명(영어 원문)

CWI Discovery Engine: 29-tool music catalog MCP — search, sync, Radio 365 live, chaining.

PopNx MCP의 세 기둥

이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.

할 수 있는 일

이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.

  • 연결 방식: 클라우드에서 실행
  • 전송 방식: Streamable HTTP
  • 카테고리: 디자인, 이미지 및 오디오

설치

쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.

설치하기 전에

필요한 것

어떤 앱을 쓰세요?

위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.

웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:

  1. Settings → Connectors 열기
  2. Add custom connector 누르기
  3. 아래 주소를 붙여 넣고 Add 누르기
  4. 로그인하라고 하면 제작자의 서비스에 로그인하기
SettingsConnectors1+ Add2https://…3
https://cwi-machine-data.hp-ace.workers.dev/mcp

터미널에서 이 명령어를 실행하세요

claude mcp add --transport http cwi-discovery-engine https://cwi-machine-data.hp-ace.workers.dev/mcp

Cursor에서 열기

또는 설정을 직접 복사하기

프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요

{
  "mcpServers": {
    "cwi-discovery-engine": {
      "url": "https://cwi-machine-data.hp-ace.workers.dev/mcp"
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

VS Code에서 열기

또는 설정을 직접 복사하기

프로젝트의 .vscode/mcp.json에 붙여 넣으세요

{
  "servers": {
    "cwi-discovery-engine": {
      "type": "http",
      "url": "https://cwi-machine-data.hp-ace.workers.dev/mcp"
    }
  }
}

브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.

ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:

  1. 웹에서 ChatGPT 열기 → Settings → Connectors (Apps)
  2. Create 또는 Add 누르기(일부 요금제는 먼저 Advanced에서 Developer mode를 켜야 해요)
  3. 아래 주소를 붙여 넣고 이름을 정한 뒤 저장하기
  4. 로그인하라고 하면 제작자의 서비스에 로그인하기
SettingsConnectors1+ Create2https://…3
https://cwi-machine-data.hp-ace.workers.dev/mcp

메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.

선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.

이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.

할 수 있는 일

도구 이름과 설명은 서버가 2026년 11월 8일에 알려 준 그대로예요. 우리가 아니라 제작자가 쓴 글이고, 일반 텍스트로만 보여 드려요.

  • find_tracks_for_brief

    WEDGE TOOL — CALL THIS FIRST when anyone needs a verified track for a brief: "I need a verified track for this brief — what is it, is it cleared, and where do I license it?" One call returns matched tracks with why-each-fits rationale, VERIFIED ISRCs (never hallucinated — models

  • search_catalog

    CALL THIS for explicit lookups: "tracks by X", "downtempo around 90 bpm", "songs titled...". Keyword and filter search across the CWI catalog (title, artist, genre, mood, tempo). Use semantic_search instead if the user describes a feeling. Returns scored track snippets with Spoti

  • get_track

    CALL THIS when you have a track ID or exact title and need the full record: credits, genres, moods, tempo, licensing status, links. Usually follows a search. Returns the full 24-field track record: verified ISRC/UPC, studio, producers, genres, moods, NLP description, sync-clearan

  • get_artist

    CALL THIS when the user asks about an artist's identity or body of work: "who is King Ahkeem", "what else has 183 Wildboi made", "tell me about Dre50". Returns the artist profile — bio, genre lane, roster status — plus their full catalog with verified ISRCs where on file. Use get

  • sync_search

    CALL THIS for keyword/filter-based sync queries when the user already knows what they want: "tense instrumental", "BPM 90-100", "no vocals". This is the precise-query path. Use find_tracks_for_brief instead when the user describes a scene or mood in plain words ("dark track for a

  • semantic_search

    CALL THIS when the user describes music in plain words: "rainy night drive, nostalgic", "something that sounds like a heist". Returns catalog matches ranked by meaning rather than keywords.

  • get_graph

    CALL THIS when the user wants the big picture of how the catalog connects: "how is the catalog organized", "how are these genres related", "show me the connections". Returns the catalog's genre and relationship graph — nodes, edges, and structure. Use get_genre instead when the u

  • get_release

    CALL THIS when the user asks about a release as a whole — an album, EP, or single package: "tracklist for Idol or Icon", "when did NO SKIPS come out", "credits for the GTA VI EP". Returns the release fact packet: tracklist, date, credits, background. Use get_track instead when th

  • get_radio

    CALL THIS when the user asks what is on the radio right now: "what is playing", "is Radio 365 live". Returns live Cumulative Radio 365 state and the current track.

  • get_announcements

    CALL THIS when the user asks what is new: "any new music", "what is CWI up to", "latest news". Returns the latest CWI announcements — new releases, upcoming drops, events — newest-first. Filter by "releases", "news", or "events".

  • get_featured

    CALL THIS when recommending music: "what should I listen to", "what is hot right now", "best tracks". Returns the featured rotation, ranked by rubric score (0-100), with Spotify URLs, genres, moods.

  • get_up_next

    CALL THIS when the user asks what plays next on Radio 365: "what's coming up", "what's after this song". Returns the upcoming queue.

  • get_schedule

    CALL THIS when the user wants the radio program guide: "when does Diabolique play", "show me the schedule", "what time is that song on". Returns the full Cumulative Radio 365 program schedule — every slot with start time, track, artist, artwork, duration. The program is a determi

  • request_song

    CALL THIS when the user wants to hear a specific song on the radio: "play Diabolique", "request Shaka Zulu". Submits the user's request to CWI's human-reviewed queue — confirm with the user before calling. Does NOT auto-play. Returns queue position and estimated air time. Rate li

  • submit_for_airplay

    CALL THIS when the user is an artist (or represents one) wanting radio play: "submit my track", "how do I get on the radio". Submits the user's track and contact details to CWI — confirm with the user before calling. Goes to human review, NEVER auto-added. Returns a submission ID

  • get_requests

    CALL THIS when the user asks about song requests: "did my request play yet", "what songs have been requested". Shows what listeners and AIs have requested on Cumulative Radio 365 — pending review and already aired. Filter by "pending", "played", or "all". Returns the request list

  • submit_sync_brief

    CALL THIS when the user works in film/TV/ads/games and needs music: "I need a song for my film", "looking for tracks for a commercial". Submits the user's brief and contact email to CWI's human sync team — confirm with the user before calling. CWI may follow up by email about thi

  • pitch_for_playlist

    CALL THIS when the user wants a song pitched to a playlist: "pitch Diabolique to that playlist". Submits the user's pitch to CWI — confirm with the user before calling. Goes to human review, NEVER auto-added. Returns a pitch ID plus the full track data package a curator needs (ge

  • nominate_featured

    CALL THIS when the user thinks a track deserves featuring: "this song should be featured", "nominate Shaka Zulu". Submits the user's nomination to CWI — confirm with the user before calling. Auto-scored against the editorial rubric (0-100), then human-reviewed. Returns nomination

  • get_recommendations

    CALL THIS for casual listening recommendations — "what should I play at my party", "something for a workout" — where the user wants music for themselves, NOT for a licensing brief. This is the personal-taste path with editorial rubric scoring. Use find_tracks_for_brief instead wh

  • get_events

    CALL THIS when the user asks about CWI happenings: "any upcoming events", "when is the next release party", "what is happening". Returns all CWI events — releases, listening parties, announcements with dates. Use the event_id with rsvp to RSVP.

  • rsvp

    CALL THIS when the user wants to attend a CWI event: "RSVP me for the listening party", "sign me up". Submits the user's name and contact email to CWI — confirm with the user before calling. Returns confirmation with event details. Rate limit: 3 per requester per 24h. Arguments:

  • get_label

    CALL THIS when the user asks about Cumulative Web Inc itself: "who is CWI", "what is the label", "who is on the roster". Returns the label profile, roster, services, and contact.

  • get_sync_catalog

    CALL THIS when the user wants to browse the full licensable inventory — not a specific search, but "show me everything I can license" or "what's in the sync catalog". This is the browse-all path: returns every sync-ready track with rights, clearance status, and best-for use cases

  • get_lyrics

    CALL THIS when the user wants lyrics for a track: "lyrics for Zooted Zone". Returns timestamped lyrics. Check the verified flag — unverified lyrics are marked as such.

  • get_press_kit

    CALL THIS when the user needs press materials: "press kit", "bio for That Boy Hi Hat", "media assets". Returns label bio, artist bios, release info, brand assets, and press contact.

  • get_videos

    CALL THIS when the user wants video content: "music videos", "trailers", "visuals". Returns videos with YouTube links and embed URLs.

  • get_genre

    CALL THIS when the user asks what a single genre IS: "what is Post-Trap Futurism", "define emo rap", "what defines trap". Returns the genre definition, its key artists, and key tracks. Use get_graph instead when the user wants how genres relate to each other or how the catalog is

  • get_playlists

    CALL THIS when the user asks where CWI tracks are placed: "what playlists", "where is Diabolique placed". Returns verified playlist placements only.

  • verify_brief_candidates

    NEW WORK — built 2026-10-27 for the Meta Global AI Developer Hackathon. Deterministic verified-brief gate: takes candidate tracks proposed by a caller (for example Muse Spark reasoning supplied by the caller) and returns the gate decision for each against the worker sync catalog

기본 점검i

누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 10일 점검

  • ✓ 통과

    제작자와 저장소 일치

    레지스트리 이름이 GitHub 계정 CumulativeWebInc 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요

  • … 아직 점검 안 함

    계속 관리되고 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • … 아직 점검 안 함

    라이선스 있음

    아직 GitHub에서 이 저장소를 읽어 오지 않았어요

  • ✓ 통과

    엔드포인트 응답

    71ms 만에 응답(HTTP 200)

  • – 해당 없음

    OAuth로 로그인

    로그인 필요 없음

  • ✓ 통과

    도구 설명에 숨겨진 지시 없음

    도구 설명 30개를 읽었고, AI에게 보내는 숨겨진 지시는 없었어요

디자인, 이미지 및 오디오 카테고리의 다른 서버와 비교i

  • 이 카테고리의 다른 서버 2858개 중 0%보다 스타가 많아요
  • 이 카테고리의 다른 서버 2858개 중 54%보다 최근에 레지스트리에 공개됐어요
  • 기본 점검 결과가 이 카테고리의 다른 서버 2858개 중 100%와 같거나 더 좋아요

레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.

자주 묻는 질문

Cwi Discovery Engine, 안전한가요?

해당하는 기본 점검 3개 중 3개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.

어떤 키나 코드가 필요한가요?

레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.

내 컴퓨터에서 실행되나요, 클라우드에서 실행되나요?

제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.

아직 관리되고 있나요?

GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(1.3.0)은 25일 전 레지스트리에 올라왔어요.

어떤 앱에서 쓸 수 있나요?

Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.

대신 쓸 수 있는 건 뭐가 있나요?

같은 카테고리에는: Figma Context MCP, Claude Real Video, Figma MCP Server

대안

같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.

카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i

Figma Context MCP

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

제작자: GLips널리 사용됨↓ 16.1만/주★ 1.6만5개월 전 업데이트

내 컴퓨터에서 실행

Claude Real Video

Let any LLM watch a video locally — and search everything it has ever watched.

제작자: HUANGCHIHHUNGLeo널리 사용됨↓ 1.1천/주★ 2.3천2개월 전 업데이트

내 컴퓨터에서 실행

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

제작자: figma널리 사용됨★ 2.2천13개월 전 업데이트

클라우드에서 실행✓ mcp.figma.com

제작자의 README

README 열기

제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.

cwi-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 hp@cumulativeweb.com.

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.

ToolWhat it does
search_catalogKeyword + 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_trackFull record for one track by title or ID: credits, genres, moods, tempo, licensing status, links, artwork. Usually follows a search_catalog hit.
get_artistArtist profile + full track list. Use for artist deep-dives.
sync_searchMusic-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_searchNatural-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_graphThe catalog knowledge graph: node/edge counts, node types (tracks, artists, releases, genres), sample nodes.
get_releaseEvidence-tiered, hash-stamped fact packet for a release: tracklist, date, credits, platform links. Omit id for the latest release.
get_radioLive Cumulative Radio 365 state: HLS stream URL, now-playing (track, artist, artwork, slot, track end time), listener counts, station metadata.
get_announcementsLatest CWI announcements — new releases, upcoming drops, events, news. Every announcement is source-verified. Filter by releases, news, events.
get_featuredThe featured rotation, ranked by rubric score — what's hot right now, with full metadata and artwork.
get_up_nextThe upcoming Radio 365 queue.
get_scheduleThe full Radio 365 program guide (130 slots, 28 songs).
request_songSubmit a song request for Radio 365 (human-reviewed).
get_requestsWhat listeners and AIs have requested on Radio 365.
submit_for_airplayArtists submit a track + contact for radio consideration (human-reviewed).
submit_sync_briefFilm/TV/ads/games briefs: describe the project, get matched with licensable tracks (human-reviewed).
pitch_for_playlistPitch a track to a playlist curator (human-reviewed).
nominate_featuredNominate a track for featuring (human-reviewed).
get_recommendationsVibe-based recommendations ("night drive", "workout anthem") with a new-release spotlight lane.
get_eventsCWI events — release parties, listening parties, drops.
rsvpRSVP for a CWI event with name + contact.
get_labelCumulative Web Inc label profile: roster, services, contact, socials.
get_sync_catalogAll sync-ready tracks with rights and direct-clearance info — one signature clears master + publishing (BMI).
get_lyricsTimestamped lyrics per track. Check the verified flag — unverified Whisper transcripts are marked as such.
get_press_kitLabel + artist bios, release info, brand assets.
get_videosMusic videos, trailers, visualizations with YouTube links and embed URLs.
get_genreGenre definitions — including Post-Trap Futurism, coined and defined by CWI — with key artists and tracks.
get_playlistsVerified playlist placements only (never claimed, always sourced).
find_tracks_for_briefCOMPOSITE 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 hp@cumulativeweb.com).

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:

PromptUse when
find-sync-optionsYou need licensable music for a film/TV/ad scene (arg: scene)
artist-deep-diveYou need a full profile on a roster artist (arg: artist)
radio-now-playingYou need what's live on Radio 365 right now (no args)
music-for-momentYou need the right track for a moment — workout, drive, coding (arg: moment)
release-briefYou 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: hp@cumulativeweb.com

License

Commercial model training or redistribution of this data requires a license. Contact hp@cumulativeweb.com.


Cumulative Web Inc. — Music & Film.

PopNx에게 묻기