Renamed to mcp-server-linkedin. This transitional package forwards to it.
Cwi Discovery Engine is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
CWI Discovery Engine is the official MCP server for the Cumulative Web Inc (CWI) music catalog — a read-only gateway to 55+ tracks from That Boy Hi Hat and the CWI roster, spanning the Post-Trap Futurism genre and beyond.MUSIC CATALOGSearch and explore the full catalog: track metadata, artist profiles, and release information across the CWI roster, including That Boy Hi Hat. Every record is machine-readable and ready for AI agents.RADIO 365Includes Radio 365 — CWI's 24/7 streaming station. The get_radio tool returns the live HLS stream, now-playing data (track, artist, artwork), and listener stats.21 PURPOSE-BUILT TOOLS- search_catalog — Search the CWI placement catalog (That Boy Hi Hat + roster) by keywords. Title matches weigh 3x, genre 2x, mood 1x. Returns top 5 tracks with Spotify URLs and matched terms.- get_track — Look up one catalog track by title or Spotify ID/URL. Returns title, artist, Spotify URL, genres, and moods.- get_artist — Look up an artist by name. Returns the artist and their tracks in the catalog with Spotify URLs.- sync_search — Search the CWI sync catalog for music-supervision queries like "fight scene" or "neon city". Built for film/TV/ad sync briefs.- semantic_search — Semantic search over the catalog embedding matrix. Ask in plain English and get ranked results with real similarity scores.- get_graph — Summarize the CWI catalog knowledge graph: 149 nodes, 269 edges covering tracks, artists, producers, releases, genres, and platforms.- get_release — Fetch a CWI release fact packet: evidence-tiered, hash-stamped pre-release and release records with verified credits, dates, and platform links.- get_radio — Tune into Cumulative Radio 365, CWI's 24/7 streaming radio station. Returns the live HLS stream URL, now-playing data, listener counts, and station metadata.- get_announcements — Get the latest CWI announcements: new releases, upcoming drops, events, and news. Filter by category or get everything newest-first.- get_featured — Get CWI's currently featured tracks with full metadata: title, artist, artwork URL, why it's featured, and stream/page links.- get_up_next — See what's queued to play next on Radio 365, with track and artist details.- get_schedule — Pull the Radio 365 program schedule: shows, times, and hosts.- request_song — Request a song to be played on Radio 365.- submit_for_airplay — Submit a track for airplay consideration on CWI's stations.- get_requests — Browse song requests made by the Radio 365 audience.- submit_sync_brief — Submit a sync brief for film, TV, or advertising placements.- pitch_for_playlist — Pitch a catalog track for playlist placement.- nominate_featured — Nominate a track to be featured by CWI.- get_recommendations — Get track recommendations from the CWI catalog.- get_events — Find upcoming CWI events: shows, releases, and appearances.- rsvp — RSVP to a CWI event.DEVELOPER TRUSTFree forever — no authentication required. Standard streamable-http MCP transport that works with Claude, Cursor, and VS Code. Plug it into any MCP-compatible client and start querying in seconds.LINKS- Website: https://cumulativeweb.com- Catalog (machine data): https://cwi-machine-data.hp-ace.workers.dev/catalog.json- MCP endpoint: https://cwi-machine-data.hp-ace.workers.dev/mcp
Watch it execute live: https://cwi-sync-scout.hp-ace.workers.dev
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http cwi-discovery-engine-mcp https://cwi-machine-data.hp-ace.workers.dev/mcp
# 2 — ask your agent for something these tools do
# find_tracks_for_brief, search_catalog, get_track and 26 more
Cwi Discovery Engine costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http cwi-discovery-engine-mcp https://cwi-machine-data.hp-ace.workers.dev/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
29 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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 cannot reliably recall these), sync-clearance status, and concrete next steps (use submit_sync_brief for human follow-up
| Parameter | Type | Required | Notes |
|---|---|---|---|
| brief | string | yes | Natural-language music brief, e.g. "tense instrumental for a heist scene". Truncated at 500 characters. |
| limit | number | no | Max tracks to return, 1-5 (default 3). |
| explicit | boolean | no | true = explicit only, false = non-explicit only. Omit for all. |
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 Spotify links, verified ISRCs, and pre-compiled try_next calls for the natural follow-up.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| 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). |
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-clearance summary, stream and presave links, related graph nodes, and try_next.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id_or_title | string | yes | Track title (exact or partial) or a Spotify track ID / open.spotify.com URL. |
CALL THIS when the user asks about an artist: "who is King Ahkeem", "what else has this artist made". Returns the artist profile and catalog.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | Artist name, e.g. "That Boy Hi Hat". |
CALL THIS when the user needs music for film, TV, ads or games: "tense instrumental for a chase scene". Returns tracks suited to the scene with direct-clearance licensing info. To start a licensing conversation, follow with submit_sync_brief.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Sync query, e.g. "club scene" or "dark aggressive". Truncated at 500 characters. |
| bpm_min | number | no | Minimum BPM (inclusive). |
| bpm_max | number | no | Maximum BPM (inclusive). |
| mood | string | no | Mood filter, matched against moods + energy words, e.g. "aggressive". |
| explicit | boolean | no | true = explicit only, false = non-explicit only. Omit for all. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Natural-language music query, e.g. "dark cyberpunk rap for a film scene". Truncated at 500 characters. |
| limit | number | no | Max results, 1-20 (default 5). |
CALL THIS when the user wants the big picture: "how is the catalog organized", "what is Post-Trap Futurism", "how are these genres related". Returns the catalog's genre and relationship graph.
No parameter schema on file.
CALL THIS when the user asks about a specific release: tracklist, date, credits, background. Returns a fact packet for that release.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | no | Release id, e.g. "cyberpunk-2027". Omit for the latest release. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| include | string | no | Optional comma-separated sections to include: "now_playing", "listeners", "stream". Omit or pass "all" for everything. Unknown values are ignored. |
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".
| Parameter | Type | Required | Notes |
|---|---|---|---|
| category | string | no | Optional filter: "releases", "news", or "events". Omit for all categories. |
| limit | number | no | Max announcements to return, 1-50 (default 10). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | number | no | Max tracks to return, 1-20 (default 10). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| count | number | no | Number of upcoming tracks to return, 1-10 (default 5). |
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 deterministic loop that repeats; times in UTC.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | string | no | Date for the schedule in YYYY-MM-DD format. Defaults to today (UTC). |
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 limit: 3 per requester name per 24h. Arguments: track_title (required), artist (required), requested_by (required — name o
| Parameter | Type | Required | Notes |
|---|---|---|---|
| track_title | string | yes | Title of the track you want to hear. |
| artist | string | yes | Artist name. |
| requested_by | string | yes | Your name or agent identity (used for rate limiting). |
| reason | string | no | Optional: why you want to hear this track. |
| dedication | string | no | Optional: who this request is dedicated to. |
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 and next steps. Arguments: artist_name, track_title, audio_url (streamable link, required), contact (email/handle, requ
| Parameter | Type | Required | Notes |
|---|---|---|---|
| artist_name | string | yes | Artist name. |
| track_title | string | yes | Track title. |
| audio_url | string | yes | Streamable URL to the track audio (required for review). |
| contact | string | yes | Email or social handle for follow-up. |
| genre | string | no | Genre of the track. |
| message | string | no | Optional pitch: why this track fits Radio 365. |
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: track title, artist, requester, status, and timestamps.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Filter by status: "pending" (awaiting review), "played" (aired), "all". Default "pending". |
| limit | number | no | Max requests to return, 1-20 (default 10). |
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 this brief. Tracks are NEVER auto-licensed. Returns a submission receipt with a tracking ID; a team member responds with cu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| scene_type | string | yes | Type of scene needing music (e.g. "car chase", "romantic montage"). |
| mood | string | yes | Mood/energy needed (e.g. "dark aggressive", "uplifting anthemic"). |
| budget_range | string | no | Optional budget range (e.g. "$1k-5k", "$10k+"). |
| deadline | string | no | Optional deadline in YYYY-MM-DD format. |
| contact | string | yes | Email for follow-up (required). |
| project_name | string | no | Optional project/film/show name. |
| description | string | no | Optional: more detail about the project or scene. |
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 (genres, moods, Spotify URL, artwork, stats). Rate limit: 3 per requester per 24h. Arguments: track_title, artist, why_fit
| Parameter | Type | Required | Notes |
|---|---|---|---|
| track_title | string | yes | Title of the track you are pitching. |
| artist | string | yes | Artist name. |
| playlist_name | string | no | Optional: target playlist name. |
| curator | string | no | Optional: curator name or handle. |
| why_fit | string | yes | Why this track fits the playlist (required). |
| contact | string | no | Optional: email for follow-up. |
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 ID, the track's rubric score, and queue position. Rate limit: 3 per requester per 24h. Arguments: track_title, artist,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| track_title | string | yes | Title of the track you are nominating. |
| artist | string | yes | Artist name. |
| nominated_by | string | yes | Your name or agent identity (required). |
| reason | string | yes | Why this track deserves the featured rotation (required). |
CALL THIS when the user describes a vibe and wants music: "something for a night drive", "workout anthem", "chill evening music", any mood-based request. Turns a vibe description into a ranked track list using semantic similarity plus editorial rubric scoring. Returns genres, moods, Spotify URLs, artwork, and why each track matches. ALSO returns a separate new_release_spotlight when CWI has an act
| Parameter | Type | Required | Notes |
|---|---|---|---|
| vibe_description | string | yes | Describe the vibe/mood you want music for. |
| count | number | no | Number of recommendations, 1-10 (default 5). |
| genre_filter | string | no | Optional genre filter (e.g. "trap", "afrobeats", "rap rock"). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| upcoming_only | boolean | no | Only show upcoming events (default true). Set false to see all. |
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: event_id (from get_events, required), name (required), contact email (required), plus_ones (optional, default 0).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| event_id | string | yes | Event ID from get_events (required). |
| name | string | yes | Your name (required). |
| contact | string | yes | Email for confirmation (required). |
| plus_ones | number | no | Number of additional guests (default 0). |
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.
No parameter schema on file.
CALL THIS when the user needs sync-ready tracks with clearance info: "what tracks can I license", "show me licensable music". Returns tracks with rights, clearance, and best-for use cases. Chain to submit_sync_brief to start licensing.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| genre | string | no | Filter by genre, e.g. "post-trap futurism". |
| mood | string | no | Filter by mood, e.g. "dark", "energetic". |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| track_id | string | yes | Track ID from get_track or search_catalog (required). |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| artist | string | no | Optional: specific artist name for their press bio. |
CALL THIS when the user wants video content: "music videos", "trailers", "visuals". Returns videos with YouTube links and embed URLs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| artist | string | no | Optional: filter by artist name. |
| type | string | no | Optional: filter by type (trailer, music-video, visualizer, live). |
CALL THIS when the user asks about a genre: "what is Post-Trap Futurism", "define emo rap". Returns the genre definition, key artists, and key tracks.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| genre | string | yes | Genre name, e.g. "post-trap futurism" (required). |
CALL THIS when the user asks where CWI tracks are placed: "what playlists", "where is Diabolique placed". Returns verified playlist placements only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| track_id | string | no | Optional: filter by track ID. |
| artist | string | no | Optional: filter by artist name. |
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Cwi Discovery Engine or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| find_tracks_for_brief | no tags | |
| search_catalog | no tags | |
| get_track | no tags | |
| get_artist | no tags | |
| sync_search | no tags | |
| semantic_search | no tags | |
| get_graph | no tags | |
| get_release | no tags | |
| get_radio | no tags | |
| get_announcements | no tags | |
| get_featured | no tags | |
| get_up_next | no tags | |
| get_schedule | no tags | |
| request_song | state-write | state-write: declares readOnlyHint: false |
| submit_for_airplay | state-write | state-write: declares readOnlyHint: false |
| get_requests | no tags | |
| submit_sync_brief | state-write | state-write: declares readOnlyHint: false |
| pitch_for_playlist | state-write | state-write: declares readOnlyHint: false |
| nominate_featured | state-write | state-write: declares readOnlyHint: false |
| get_recommendations | no tags | |
| get_events | no tags | |
| rsvp | state-write | state-write: declares readOnlyHint: false |
| get_label | no tags | |
| get_sync_catalog | untrusted-input | untrusted-input: keyword "browse" |
| get_lyrics | no tags | |
| get_press_kit | no tags | |
| get_videos | no tags | |
| get_genre | no tags | |
| get_playlists | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.3.0.
No release note was published with this version.
- Expanded the tool surface from 21 to 29 tools: find_tracks_for_brief, get_announcements, get_artist, get_events, get_featured, get_genre, get_graph, get_label, get_lyrics, get_playlists, get_press_kit, get_radio, get_recommendations, get_release, get_requests, get_schedule, get_sync_catalog, get_track, get_up_next, get_videos, nominate_featured, pitch_for_playlist, request_song, rsvp, search_catalog, semantic_search, submit_for_airplay, submit_sync_brief, sync_search.
- Expanded the tool surface from 10 to 21 tools. New in 1.1.0: get_up_next, get_schedule, request_song, submit_for_airplay, get_requests, submit_sync_brief, pitch_for_playlist, nominate_featured, get_recommendations, get_events, and rsvp — covering Radio 365 scheduling and requests, airplay submissions, sync briefs, playlist pitching, featured nominations, recommendations, and events.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish Cwi Discovery Engine can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.