CWI Discovery Engine MCP
A 29-tool MCP server providing AI agents with access to the Cumulative Web Inc music catalog. It supports search, sync licensing discovery, radio streaming, and curation tools with verified ISRCs and one-signature clearance for commercial use.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
MCP endpoint (Streamable HTTP)
https://cwi-machine-data.hp-ace.workers.dev/mcpWhat its tools do
30 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Read-only (24)
find_tracks_for_briefsearch_catalogget_trackget_artistsync_searchsemantic_searchget_graphget_releaseget_radioget_announcementsget_featuredget_up_nextget_scheduleget_requestsget_recommendationsget_eventsget_labelget_sync_catalogget_lyricsget_press_kitget_videosget_genreget_playlistsverify_brief_candidates
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Warning Advertises resources/templates/list but does not implement it
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Search the music catalog by genre or mood
- Find tracks for sync licensing briefs
- Access live radio schedules and streams
- Retrieve artist and track metadata
Source and maintenance
Community listingRegistry 1.3.0
- Maintenance checked
Protocol and capabilities
- Server
- cwi-catalog-mcp 1.0.0
- MCP protocol negotiated in check
- 2024-11-05
- Tools
- 30 advertised
- Resources
- 3 advertised
- Resource templates
- Not advertised
- Prompts
- 5 advertised
Server-advertised capabilities
{
"tools": {},
"prompts": {
"listChanged": false
},
"resources": {
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
30 advertised
find_tracks_for_brief — Find Tracks for a Brief
Advertised read-only
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). Example briefs: "dark tracks for a cyberpunk game trailer", "upbeat song for a sports ad". A match is NOT a license grant — clearance still requires a brief. Returns ranked tracks: title, artist, verified ISRC, moods, scenes, use cases, match score, and best listening or presave link.
find_tracks_for_brief input schema
{
"type": "object",
"required": [
"brief"
],
"properties": {
"brief": {
"type": "string",
"description": "Natural-language music brief, e.g. \"tense instrumental for a heist scene\". Truncated at 500 characters."
},
"limit": {
"type": "number",
"description": "Max tracks to return, 1-5 (default 3)."
},
"explicit": {
"type": "boolean",
"description": "true = explicit only, false = non-explicit only. Omit for all."
}
}
}find_tracks_for_brief output schema
{
"type": "object",
"required": [
"brief",
"count",
"tracks",
"clearance_summary",
"licensing_disclaimer",
"next_steps"
],
"properties": {
"brief": {
"type": "string"
},
"count": {
"type": "integer"
},
"tokens": {
"type": "array",
"items": {
"type": "string"
}
},
"tracks": {
"type": "array",
"items": {
"type": "object",
"properties": {
"isrc": {
"type": [
"string",
"null"
],
"description": "Verified ISRC from the query-db, or null when not on file. Never invented."
},
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"score": {
"type": "number"
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"scenes": {
"type": "array",
"items": {
"type": "string"
}
},
"explicit": {
"type": [
"boolean",
"string"
]
},
"track_id": {
"type": "string"
},
"best_link": {
"type": [
"object",
"null"
],
"description": "Best available listen link: presave (unreleased) > Spotify > Apple Music, with kind label.",
"additionalProperties": true
},
"use_cases": {
"type": "array",
"items": {
"type": "string"
}
},
"spotify_url": {
"type": "string"
},
"why_it_fits": {
"type": "array",
"items": {
"type": "string"
},
"description": "Concrete descriptor matches, e.g. 'mood: aggressive', 'scene: fight scene'."
},
"isrc_verified": {
"type": "boolean"
}
},
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"next_steps": {
"type": "array",
"items": {
"type": "string"
},
"description": "Concrete actions: submit_sync_brief with the brief, contact email, license terms URL."
},
"generated_at": {
"type": "string"
},
"clearance_summary": {
"type": "string",
"description": "Plain-language clearance status for the matched tracks: who controls master+publishing, one-signature terms, PRO."
},
"licensing_disclaimer": {
"type": "string",
"description": "States that a match is not a license grant."
}
},
"description": "find_tracks_for_brief response: matched tracks with fit reasons, verified ISRCs, clearance summary, next steps.",
"additionalProperties": true
}find_tracks_for_brief annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}search_catalog — Search Catalog
Advertised read-only
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.
search_catalog input schema
{
"type": "object",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Search keywords, e.g. \"cyberpunk rap\" or \"dark cinematic\". Truncated at 500 characters."
},
"limit": {
"type": "number",
"description": "Max tracks to return, 1-10 (default 5)."
}
}
}search_catalog output schema
{
"type": "object",
"required": [
"query",
"count",
"results"
],
"properties": {
"count": {
"type": "integer"
},
"limit": {
"type": "integer"
},
"query": {
"type": "string"
},
"tokens": {
"type": "array",
"items": {
"type": "string"
}
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"genres": {
"type": "array",
"items": {
"type": "string"
}
},
"featured": {
"type": "boolean"
},
"graph_node": {
"type": "string",
"description": "Knowledge-graph node id, e.g. track:cyberpunk-2027."
}
},
"description": "Track snippet (list views carry a snippet, not the full prose description).",
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"new_release_spotlight": {
"type": "object",
"description": "Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.",
"additionalProperties": true
}
},
"description": "search_catalog response: scored track snippets plus pre-compiled try_next calls.",
"additionalProperties": true
}search_catalog annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_track — Get Track Details
Advertised read-only
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.
get_track input schema
{
"type": "object",
"required": [
"id_or_title"
],
"properties": {
"id_or_title": {
"type": "string",
"description": "Track title (exact or partial) or a Spotify track ID / open.spotify.com URL."
}
}
}get_track output schema
{
"type": "object",
"required": [
"track_id",
"title",
"artist"
],
"properties": {
"upc": {
"type": [
"string",
"null"
]
},
"isrc": {
"type": [
"string",
"null"
]
},
"mbid": {
"type": [
"string",
"null"
],
"description": "MusicBrainz recording MBID."
},
"album": {
"type": [
"string",
"null"
]
},
"label": {
"type": [
"string",
"null"
]
},
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"genres": {
"type": "array",
"items": {
"type": "string"
}
},
"scenes": {
"type": "array",
"items": {
"type": "string"
}
},
"studio": {
"type": [
"string",
"null"
]
},
"credits": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"contexts": {
"type": "array",
"items": {
"type": "string"
}
},
"engineer": {
"type": [
"string",
"null"
]
},
"featured": {
"type": "boolean"
},
"track_id": {
"type": "string"
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"producers": {
"type": "array",
"items": {
"type": "string"
}
},
"signature": {
"type": [
"object",
"null"
],
"description": "That Boy Hi Hat flow-architecture signature block (present on his tracks).",
"additionalProperties": true
},
"use_cases": {
"type": "array",
"items": {
"type": "string"
}
},
"graph_node": {
"type": "string"
},
"artist_mbid": {
"type": [
"string",
"null"
],
"description": "MusicBrainz artist MBID."
},
"artwork_url": {
"type": [
"string",
"null"
]
},
"description": {
"type": "string",
"description": "150-300 word NLP prose (Whisper-derived where flagged; not proofread)."
},
"presave_url": {
"type": [
"string",
"null"
]
},
"spotify_url": {
"type": "string"
},
"release_date": {
"type": [
"string",
"null"
],
"description": "Original commercial release date (YYYY-MM-DD)."
},
"related_nodes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 8 connected knowledge-graph node IDs."
},
"streaming_urls": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"apple_music_url": {
"type": "string"
},
"summary_markdown": {
"type": "string",
"description": "Compact markdown: title, ISRC/UPC, studio, genres/moods, one-line sync clearance."
},
"sounds_like_lanes": {
"type": "array",
"items": {
"type": "string"
}
}
},
"description": "get_track response: full 24-field track record plus summary_markdown, related_nodes, try_next.",
"additionalProperties": true
}get_track annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_artist — Get Artist Profile
Advertised read-only
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_track when the user asks about one specific song.
get_artist input schema
{
"type": "object",
"required": [
"name"
],
"properties": {
"name": {
"type": "string",
"description": "Artist name, e.g. \"That Boy Hi Hat\"."
}
}
}get_artist output schema
{
"type": "object",
"required": [
"artist",
"track_count",
"tracks"
],
"properties": {
"artist": {
"type": "string"
},
"tracks": {
"type": "array",
"items": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"spotify_url": {
"type": "string"
}
},
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"track_count": {
"type": "integer"
},
"related_nodes": {
"type": "array",
"items": {
"type": "string"
},
"description": "Up to 8 connected knowledge-graph node IDs."
}
},
"description": "get_artist response: artist profile, catalog list, related graph nodes.",
"additionalProperties": true
}get_artist annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}sync_search — Search Sync Catalog
Advertised read-only
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 heist scene") — the wedge handles natural language and adds why-it-fits rationale. Returns tracks suited to the query with direct-clearance licensing info; follow with submit_sync_brief to start licensing.
sync_search input schema
{
"type": "object",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Sync query, e.g. \"club scene\" or \"dark aggressive\". Truncated at 500 characters."
},
"mood": {
"type": "string",
"description": "Mood filter, matched against moods + energy words, e.g. \"aggressive\"."
},
"bpm_max": {
"type": "number",
"description": "Maximum BPM (inclusive)."
},
"bpm_min": {
"type": "number",
"description": "Minimum BPM (inclusive)."
},
"explicit": {
"type": "boolean",
"description": "true = explicit only, false = non-explicit only. Omit for all."
}
}
}sync_search output schema
{
"type": "object",
"required": [
"query",
"count",
"results"
],
"properties": {
"count": {
"type": "integer"
},
"query": {
"type": "string"
},
"tokens": {
"type": "array",
"items": {
"type": "string"
}
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"score": {
"type": "number"
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"rights": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"scenes": {
"type": "array",
"items": {
"type": "string"
}
},
"credits": {
"type": "string"
},
"track_id": {
"type": "string"
},
"use_cases": {
"type": "array",
"items": {
"type": "string"
}
},
"musical_key": {
"type": [
"string",
"null"
]
},
"licensing_terms_pointer": {
"type": "string"
}
},
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"license_block": {
"type": "string",
"description": "Markdown licensing summary for the top hit: ISRC, rights holders, clearance terms, contact."
},
"filters_applied": {
"type": "object",
"additionalProperties": true
},
"descriptor_provenance": {
"type": "string"
}
},
"description": "sync_search response: scene-matched tracks with rights info, plus a license_block for the top hit.",
"additionalProperties": true
}sync_search annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}semantic_search — Semantic Music Search
Advertised read-only
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.
semantic_search input schema
{
"type": "object",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"description": "Natural-language music query, e.g. \"dark cyberpunk rap for a film scene\". Truncated at 500 characters."
},
"limit": {
"type": "number",
"description": "Max results, 1-20 (default 5)."
}
}
}semantic_search output schema
{
"type": "object",
"required": [
"query",
"method",
"count",
"results"
],
"properties": {
"dim": {
"type": "integer"
},
"count": {
"type": "integer"
},
"limit": {
"type": "integer"
},
"model": {
"type": "string"
},
"query": {
"type": "string"
},
"method": {
"type": "string",
"description": "cosine:<model> or fallback:keyword."
},
"results": {
"type": "array",
"items": {
"type": "object",
"properties": {
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"genres": {
"type": "array",
"items": {
"type": "string"
}
},
"featured": {
"type": "boolean"
},
"graph_node": {
"type": "string",
"description": "Knowledge-graph node id, e.g. track:cyberpunk-2027."
}
},
"description": "Track snippet (list views carry a snippet, not the full prose description).",
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"fallback": {
"type": "boolean"
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"fallback_note": {
"type": "string"
}
},
"description": "semantic_search response: cosine- or keyword-ranked tracks for a natural-language mood query.",
"additionalProperties": true
}semantic_search annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_graph — Get Catalog Graph
Advertised read-only
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 user asks what one specific genre is.
get_graph input schema
{
"type": "object",
"properties": {}
}get_graph output schema
{
"type": "object",
"required": [
"source",
"full_graph"
],
"properties": {
"source": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"full_graph": {
"type": "string"
},
"generated_at": {
"type": "string"
}
},
"description": "get_graph response: catalog knowledge-graph summary (node/edge counts, samples), not the full graph.",
"additionalProperties": true
}get_graph annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_release — Get Release Info
Advertised read-only
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 the user asks about one specific song.
get_release input schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Release id, e.g. \"cyberpunk-2027\". Omit for the latest release."
}
}
}get_release output schema
{
"type": "object",
"required": [
"id",
"found"
],
"properties": {
"id": {
"type": "string"
},
"found": {
"type": "boolean"
},
"packet": {
"type": "object",
"description": "Fact packet: facts list of {claim, evidence{source, observed}, tier}.",
"additionalProperties": true
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"known_releases": {
"type": "array",
"items": {
"type": "string"
}
},
"new_release_spotlight": {
"type": "object",
"description": "Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.",
"additionalProperties": true
}
},
"description": "get_release response: release fact packet (claims with evidence tiers) or not-found.",
"additionalProperties": true
}get_release annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_radio — Get Radio Status
Advertised read-only
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_radio input schema
{
"type": "object",
"properties": {
"include": {
"type": "string",
"description": "Optional comma-separated sections to include: \"now_playing\", \"listeners\", \"stream\". Omit or pass \"all\" for everything. Unknown values are ignored."
}
}
}get_radio output schema
{
"type": "object",
"required": [
"station",
"station_url"
],
"properties": {
"stream": {
"type": "object",
"additionalProperties": true
},
"station": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"listeners": {
"type": "object",
"additionalProperties": true
},
"now_playing": {
"type": "object",
"additionalProperties": true
},
"station_url": {
"type": "string"
},
"generated_at": {
"type": "string"
},
"proof_of_airplay": {
"type": "object",
"additionalProperties": true
}
},
"description": "get_radio response: live Radio 365 state — stream, now-playing, listeners, proof-of-airplay.",
"additionalProperties": true
}get_radio annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_announcements — Get Announcements
Advertised read-only
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_announcements input schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max announcements to return, 1-50 (default 10)."
},
"category": {
"type": "string",
"description": "Optional filter: \"releases\", \"news\", or \"events\". Omit for all categories."
}
}
}get_announcements output schema
{
"type": "object",
"required": [
"count",
"announcements"
],
"properties": {
"count": {
"type": "integer"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"category": {
"type": "string"
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"announcements": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"data_updated_at": {
"type": [
"string",
"null"
]
}
},
"description": "get_announcements response: CWI announcements newest-first.",
"additionalProperties": true
}get_announcements annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_featured — Get Featured Tracks
Advertised read-only
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_featured input schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max tracks to return, 1-20 (default 10)."
}
}
}get_featured output schema
{
"type": "object",
"required": [
"count",
"featured"
],
"properties": {
"count": {
"type": "integer"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"featured": {
"type": "array",
"items": {
"type": "object",
"properties": {
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"score": {
"type": [
"number",
"null"
]
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"genres": {
"type": "array",
"items": {
"type": "string"
}
},
"graph_node": {
"type": [
"string",
"null"
]
},
"why_featured": {
"type": "object",
"additionalProperties": true
}
},
"additionalProperties": true
}
},
"rotation": {
"type": [
"string",
"null"
]
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"rotation_raw": {
"type": [
"string",
"null"
]
},
"data_updated_at": {
"type": [
"string",
"null"
]
},
"new_release_spotlight": {
"type": "object",
"description": "Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.",
"additionalProperties": true
}
},
"description": "get_featured response: featured rotation ranked by rubric score (0-100).",
"additionalProperties": true
}get_featured annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_up_next — Get Up Next on Radio
Advertised read-only
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_up_next input schema
{
"type": "object",
"properties": {
"count": {
"type": "number",
"description": "Number of upcoming tracks to return, 1-10 (default 5)."
}
}
}get_up_next output schema
{
"type": "object",
"required": [
"station",
"now_playing",
"up_next"
],
"properties": {
"note": {
"type": "string"
},
"count": {
"type": "integer"
},
"station": {
"type": "string"
},
"up_next": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"stream_url": {
"type": "string"
},
"now_playing": {
"type": "object",
"additionalProperties": true
},
"generated_at": {
"type": "string"
},
"program_version": {
"type": [
"string",
"null"
]
}
},
"description": "get_up_next response: now-playing plus the upcoming Radio 365 queue with air times (UTC).",
"additionalProperties": true
}get_up_next annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_schedule — Get Radio Schedule
Advertised read-only
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.
get_schedule input schema
{
"type": "object",
"properties": {
"date": {
"type": "string",
"description": "Date for the schedule in YYYY-MM-DD format. Defaults to today (UTC)."
}
}
}get_schedule output schema
{
"type": "object",
"required": [
"station",
"slot_count",
"slots"
],
"properties": {
"date": {
"type": "string"
},
"note": {
"type": "string"
},
"slots": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"station": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"slot_count": {
"type": "integer"
},
"stream_url": {
"type": "string"
},
"generated_at": {
"type": "string"
},
"period_seconds": {
"type": [
"number",
"null"
]
},
"program_version": {
"type": [
"string",
"null"
]
}
},
"description": "get_schedule response: full Radio 365 rotation — every slot with track, artist, duration, next air time (UTC).",
"additionalProperties": true
}get_schedule annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}request_song — Request a 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 limit: 3 per requester name per 24h. Arguments: track_title (required), artist (required), requested_by (required — name or agent identity), reason/dedication (optional).
request_song input schema
{
"type": "object",
"required": [
"track_title",
"artist",
"requested_by"
],
"properties": {
"artist": {
"type": "string",
"description": "Artist name."
},
"reason": {
"type": "string",
"description": "Optional: why you want to hear this track."
},
"dedication": {
"type": "string",
"description": "Optional: who this request is dedicated to."
},
"track_title": {
"type": "string",
"description": "Title of the track you want to hear."
},
"requested_by": {
"type": "string",
"description": "Your name or agent identity (used for rate limiting)."
}
}
}request_song output schema
{
"type": "object",
"required": [
"ok",
"request_id",
"status"
],
"properties": {
"ok": {
"type": "boolean"
},
"artist": {
"type": "string"
},
"review": {
"type": "string"
},
"status": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"request_id": {
"type": [
"integer",
"null"
]
},
"track_title": {
"type": "string"
},
"requested_at": {
"type": "string"
},
"requested_by": {
"type": "string"
},
"queue_position": {
"type": "integer"
},
"estimated_air_in_minutes": {
"type": "integer"
}
},
"description": "request_song response: queued request with ID, queue position, ETA. Human-reviewed; never auto-plays.",
"additionalProperties": true
}request_song annotations
{
"readOnlyHint": false,
"idempotentHint": false,
"destructiveHint": false
}submit_for_airplay — 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 and next steps. Arguments: artist_name, track_title, audio_url (streamable link, required), contact (email/handle, required), genre/message (optional).
submit_for_airplay input schema
{
"type": "object",
"required": [
"artist_name",
"track_title",
"audio_url",
"contact"
],
"properties": {
"genre": {
"type": "string",
"description": "Genre of the track."
},
"contact": {
"type": "string",
"description": "Email or social handle for follow-up."
},
"message": {
"type": "string",
"description": "Optional pitch: why this track fits Radio 365."
},
"audio_url": {
"type": "string",
"description": "Streamable URL to the track audio (required for review)."
},
"artist_name": {
"type": "string",
"description": "Artist name."
},
"track_title": {
"type": "string",
"description": "Track title."
}
}
}submit_for_airplay output schema
{
"type": "object",
"required": [
"ok",
"submission_id",
"status"
],
"properties": {
"ok": {
"type": "boolean"
},
"genre": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"artist_name": {
"type": "string"
},
"review_note": {
"type": "string"
},
"track_title": {
"type": "string"
},
"submitted_at": {
"type": "string"
},
"submission_id": {
"type": [
"integer",
"null"
]
},
"what_happens_next": {
"type": "string"
}
},
"description": "submit_for_airplay response: submission ID and review status. Human-reviewed; never auto-added.",
"additionalProperties": true
}submit_for_airplay annotations
{
"readOnlyHint": false,
"idempotentHint": false,
"destructiveHint": false
}get_requests — Get Song Requests
Advertised read-only
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.
get_requests input schema
{
"type": "object",
"properties": {
"limit": {
"type": "number",
"description": "Max requests to return, 1-20 (default 10)."
},
"status": {
"type": "string",
"description": "Filter by status: \"pending\" (awaiting review), \"played\" (aired), \"all\". Default \"pending\"."
}
}
}get_requests output schema
{
"type": "object",
"required": [
"station",
"count",
"requests"
],
"properties": {
"note": {
"type": "string"
},
"count": {
"type": "integer"
},
"station": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"requests": {
"type": "array",
"items": {
"type": "object",
"properties": {
"artist": {
"type": "string"
},
"reason": {
"type": [
"string",
"null"
]
},
"status": {
"type": "string"
},
"dedication": {
"type": [
"string",
"null"
]
},
"request_id": {
"type": "integer"
},
"track_title": {
"type": "string"
},
"requested_at": {
"type": "string"
},
"requested_by": {
"type": "string"
}
},
"additionalProperties": true
}
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"pending_count": {
"type": "integer"
},
"status_filter": {
"type": "string"
}
},
"description": "get_requests response: song-request queue (pending/played/all).",
"additionalProperties": true
}get_requests annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}submit_sync_brief — 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 this brief. Tracks are NEVER auto-licensed. Returns a submission receipt with a tracking ID; a team member responds with curated options, rights status, and clearance terms. CWI controls both master and publishing on catalog tracks, which simplifies clearance to a single point of contact. Rate limit: 3 per requester per 24h. Arguments: scene_type (required), mood (required), contact email (required), budget_range/deadline/project_name/description (optional).
submit_sync_brief input schema
{
"type": "object",
"required": [
"scene_type",
"mood",
"contact"
],
"properties": {
"mood": {
"type": "string",
"description": "Mood/energy needed (e.g. \"dark aggressive\", \"uplifting anthemic\")."
},
"contact": {
"type": "string",
"description": "Email for follow-up (required)."
},
"deadline": {
"type": "string",
"description": "Optional deadline in YYYY-MM-DD format."
},
"scene_type": {
"type": "string",
"description": "Type of scene needing music (e.g. \"car chase\", \"romantic montage\")."
},
"description": {
"type": "string",
"description": "Optional: more detail about the project or scene."
},
"budget_range": {
"type": "string",
"description": "Optional budget range (e.g. \"$1k-5k\", \"$10k+\")."
},
"project_name": {
"type": "string",
"description": "Optional project/film/show name."
}
}
}submit_sync_brief output schema
{
"type": "object",
"required": [
"ok",
"brief_id",
"status"
],
"properties": {
"ok": {
"type": "boolean"
},
"mood": {
"type": "string"
},
"status": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"brief_id": {
"type": [
"integer",
"null"
]
},
"deadline": {
"type": [
"string",
"null"
]
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"scene_type": {
"type": "string"
},
"rights_note": {
"type": "string"
},
"budget_range": {
"type": [
"string",
"null"
]
},
"project_name": {
"type": [
"string",
"null"
]
},
"submitted_at": {
"type": "string"
},
"license_block": {
"type": "string",
"description": "Markdown licensing summary: rights holders, clearance terms, contact."
},
"what_happens_next": {
"type": "string"
}
},
"description": "submit_sync_brief response: brief ID, review status, and a license_block markdown summary.",
"additionalProperties": true
}submit_sync_brief annotations
{
"readOnlyHint": false,
"idempotentHint": false,
"destructiveHint": false
}pitch_for_playlist — 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 (genres, moods, Spotify URL, artwork, stats). Rate limit: 3 per requester per 24h. Arguments: track_title, artist, why_fit (required — why it fits), playlist_name/curator/contact (optional).
pitch_for_playlist input schema
{
"type": "object",
"required": [
"track_title",
"artist",
"why_fit"
],
"properties": {
"artist": {
"type": "string",
"description": "Artist name."
},
"contact": {
"type": "string",
"description": "Optional: email for follow-up."
},
"curator": {
"type": "string",
"description": "Optional: curator name or handle."
},
"why_fit": {
"type": "string",
"description": "Why this track fits the playlist (required)."
},
"track_title": {
"type": "string",
"description": "Title of the track you are pitching."
},
"playlist_name": {
"type": "string",
"description": "Optional: target playlist name."
}
}
}pitch_for_playlist output schema
{
"type": "object",
"required": [
"ok",
"pitch_id",
"status"
],
"properties": {
"ok": {
"type": "boolean"
},
"note": {
"type": "string"
},
"artist": {
"type": "string"
},
"review": {
"type": "string"
},
"status": {
"type": "string"
},
"curator": {
"type": [
"string",
"null"
]
},
"receipt": {
"type": "object",
"required": [
"id",
"status",
"received_at"
],
"properties": {
"id": {
"type": [
"integer",
"null"
]
},
"status": {
"type": "string"
},
"received_at": {
"type": "string"
}
},
"description": "Confirmation receipt; id is the real intake row id.",
"additionalProperties": false
},
"why_fit": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"pitch_id": {
"type": [
"integer",
"null"
]
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"track_data": {
"type": [
"object",
"null"
],
"additionalProperties": true
},
"track_title": {
"type": "string"
},
"submitted_at": {
"type": "string"
},
"playlist_name": {
"type": [
"string",
"null"
]
}
},
"description": "pitch_for_playlist response: pitch ID, review status, and a receipt with the real D1 row id.",
"additionalProperties": true
}pitch_for_playlist annotations
{
"readOnlyHint": false,
"idempotentHint": false,
"destructiveHint": false
}nominate_featured — Nominate Featured Track
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, nominated_by (required), reason (required).
nominate_featured input schema
{
"type": "object",
"required": [
"track_title",
"artist",
"nominated_by",
"reason"
],
"properties": {
"artist": {
"type": "string",
"description": "Artist name."
},
"reason": {
"type": "string",
"description": "Why this track deserves the featured rotation (required)."
},
"track_title": {
"type": "string",
"description": "Title of the track you are nominating."
},
"nominated_by": {
"type": "string",
"description": "Your name or agent identity (required)."
}
}
}nominate_featured output schema
{
"type": "object",
"required": [
"ok",
"nomination_id",
"status"
],
"properties": {
"ok": {
"type": "boolean"
},
"artist": {
"type": "string"
},
"review": {
"type": "string"
},
"status": {
"type": "string"
},
"receipt": {
"type": "object",
"required": [
"id",
"status",
"received_at"
],
"properties": {
"id": {
"type": [
"integer",
"null"
]
},
"status": {
"type": "string"
},
"received_at": {
"type": "string"
}
},
"description": "Confirmation receipt; id is the real intake row id.",
"additionalProperties": false
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"graph_node": {
"type": [
"string",
"null"
]
},
"rubric_note": {
"type": "string"
},
"track_title": {
"type": "string"
},
"nominated_by": {
"type": "string"
},
"rubric_score": {
"type": [
"number",
"null"
]
},
"submitted_at": {
"type": "string"
},
"nomination_id": {
"type": [
"integer",
"null"
]
},
"queue_position": {
"type": "integer"
},
"in_current_rotation": {
"type": "boolean"
}
},
"description": "nominate_featured response: nomination ID, rubric score, and a receipt with the real D1 row id.",
"additionalProperties": true
}nominate_featured annotations
{
"readOnlyHint": false,
"idempotentHint": false,
"destructiveHint": false
}get_recommendations — Get Music Recommendations
Advertised read-only
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 when the request is for a project (film, ad, game, trailer) — the wedge adds verified ISRCs and clearance info that recommendations don't. Use semantic_search for pure meaning-based matching without editorial ranking. Returns genres, moods, Spotify URLs, artwork, and why each track matches. ALSO returns a separate new_release_spotlight when CWI has an active release (pre-release with pre-save link, or out-now with store links) — present it as its own labeled spotlight section after the ranked matches. Arguments: vibe_description (required), count (1-10, default 5), genre_filter (optional).
get_recommendations input schema
{
"type": "object",
"required": [
"vibe_description"
],
"properties": {
"count": {
"type": "number",
"description": "Number of recommendations, 1-10 (default 5)."
},
"genre_filter": {
"type": "string",
"description": "Optional genre filter (e.g. \"trap\", \"afrobeats\", \"rap rock\")."
},
"vibe_description": {
"type": "string",
"description": "Describe the vibe/mood you want music for."
}
}
}get_recommendations output schema
{
"type": "object",
"required": [
"vibe_description",
"method",
"count",
"recommendations"
],
"properties": {
"note": {
"type": "string"
},
"count": {
"type": "integer"
},
"method": {
"type": "string"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"genre_filter": {
"type": [
"string",
"null"
]
},
"recommendations": {
"type": "array",
"items": {
"type": "object",
"properties": {
"rank": {
"type": "integer"
},
"moods": {
"type": "array",
"items": {
"type": "string"
}
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
},
"genres": {
"type": "array",
"items": {
"type": "string"
}
},
"graph_node": {
"type": [
"string",
"null"
]
},
"match_score": {
"type": [
"number",
"null"
]
},
"why_matches": {
"type": "string"
},
"rubric_score": {
"type": [
"number",
"null"
]
}
},
"additionalProperties": true
}
},
"vibe_description": {
"type": "string"
},
"new_release_spotlight": {
"type": [
"object",
"null"
],
"additionalProperties": true
}
},
"description": "get_recommendations response: vibe-ranked tracks plus an editorial new-release spotlight.",
"additionalProperties": true
}get_recommendations annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_events — Get Events
Advertised read-only
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.
get_events input schema
{
"type": "object",
"properties": {
"upcoming_only": {
"type": "boolean",
"description": "Only show upcoming events (default true). Set false to see all."
}
}
}get_events output schema
{
"type": "object",
"required": [
"count",
"events"
],
"properties": {
"note": {
"type": "string"
},
"count": {
"type": "integer"
},
"events": {
"type": "array",
"items": {
"type": "object",
"properties": {
"date": {
"type": "string"
},
"type": {
"type": "string"
},
"links": {
"type": "object",
"additionalProperties": true
},
"title": {
"type": "string"
},
"event_id": {
"type": "string"
},
"description": {
"type": "string"
}
},
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"generated_at": {
"type": "string"
},
"upcoming_only": {
"type": "boolean"
}
},
"description": "get_events response: CWI events (releases, listening parties, recurring).",
"additionalProperties": true
}get_events annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}rsvp — RSVP to Event
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).
rsvp input schema
{
"type": "object",
"required": [
"event_id",
"name",
"contact"
],
"properties": {
"name": {
"type": "string",
"description": "Your name (required)."
},
"contact": {
"type": "string",
"description": "Email for confirmation (required)."
},
"event_id": {
"type": "string",
"description": "Event ID from get_events (required)."
},
"plus_ones": {
"type": "number",
"description": "Number of additional guests (default 0)."
}
}
}rsvp output schema
{
"type": "object",
"required": [
"ok",
"rsvp_id",
"status"
],
"properties": {
"ok": {
"type": "boolean"
},
"name": {
"type": "string"
},
"status": {
"type": "string"
},
"rsvp_at": {
"type": "string"
},
"rsvp_id": {
"type": [
"integer",
"null"
]
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"event_id": {
"type": "string"
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"plus_ones": {
"type": "integer"
},
"event_title": {
"type": "string"
},
"confirmation": {
"type": "string"
}
},
"description": "rsvp response: RSVP confirmation with ID. Rate limit: 3 per contact per 24h.",
"additionalProperties": true
}rsvp annotations
{
"readOnlyHint": false,
"idempotentHint": false,
"destructiveHint": false
}get_label — Get Label Profile
Advertised read-only
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_label input schema
{
"type": "object",
"properties": {}
}get_label output schema
{
"type": "object",
"required": [
"ok",
"label"
],
"properties": {
"ok": {
"type": "boolean"
},
"label": {
"type": "object",
"additionalProperties": true
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
}
},
"description": "get_label response: Cumulative Web Inc label profile, roster, services, contact.",
"additionalProperties": true
}get_label annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_sync_catalog — Get Sync Catalog
Advertised read-only
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. Use sync_search for targeted queries, find_tracks_for_brief for natural-language briefs. Chain to submit_sync_brief to start licensing.
get_sync_catalog input schema
{
"type": "object",
"properties": {
"mood": {
"type": "string",
"description": "Filter by mood, e.g. \"dark\", \"energetic\"."
},
"genre": {
"type": "string",
"description": "Filter by genre, e.g. \"post-trap futurism\"."
}
}
}get_sync_catalog output schema
{
"type": "object",
"required": [
"ok",
"tracks",
"count"
],
"properties": {
"ok": {
"type": "boolean"
},
"note": {
"type": "string"
},
"count": {
"type": "integer"
},
"tracks": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
}
},
"description": "get_sync_catalog response: sync-ready tracks with rights and clearance info.",
"additionalProperties": true
}get_sync_catalog annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_lyrics — Get Lyrics
Advertised read-only
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_lyrics input schema
{
"type": "object",
"required": [
"track_id"
],
"properties": {
"track_id": {
"type": "string",
"description": "Track ID from get_track or search_catalog (required)."
}
}
}get_lyrics output schema
{
"type": "object",
"required": [
"ok",
"found"
],
"properties": {
"ok": {
"type": "boolean"
},
"note": {
"type": "string"
},
"found": {
"type": "boolean"
},
"lyrics": {
"type": "object",
"additionalProperties": true
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"track_id": {
"type": "string"
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
}
},
"description": "get_lyrics response: timestamped lyrics when on file; found:false with note otherwise.",
"additionalProperties": true
}get_lyrics annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_press_kit — Get Press Kit
Advertised read-only
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_press_kit input schema
{
"type": "object",
"properties": {
"artist": {
"type": "string",
"description": "Optional: specific artist name for their press bio."
}
}
}get_press_kit output schema
{
"type": "object",
"required": [
"ok",
"press_kit"
],
"properties": {
"ok": {
"type": "boolean"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"press_kit": {
"type": "object",
"additionalProperties": true
}
},
"description": "get_press_kit response: label bio, artist bios, release info, brand assets, press contact.",
"additionalProperties": true
}get_press_kit annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_videos — Get Videos
Advertised read-only
CALL THIS when the user wants video content: "music videos", "trailers", "visuals". Returns videos with YouTube links and embed URLs.
get_videos input schema
{
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Optional: filter by type (trailer, music-video, visualizer, live)."
},
"artist": {
"type": "string",
"description": "Optional: filter by artist name."
}
}
}get_videos output schema
{
"type": "object",
"required": [
"ok",
"videos",
"count"
],
"properties": {
"ok": {
"type": "boolean"
},
"count": {
"type": "integer"
},
"videos": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
}
},
"description": "get_videos response: videos with YouTube links and embed URLs.",
"additionalProperties": true
}get_videos annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_genre — Get Genre Info
Advertised read-only
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 organized as a whole.
get_genre input schema
{
"type": "object",
"required": [
"genre"
],
"properties": {
"genre": {
"type": "string",
"description": "Genre name, e.g. \"post-trap futurism\" (required)."
}
}
}get_genre output schema
{
"type": "object",
"required": [
"ok",
"found"
],
"properties": {
"ok": {
"type": "boolean"
},
"found": {
"type": "boolean"
},
"genre": {
"type": [
"object",
"string"
],
"additionalProperties": true
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"available_genres": {
"type": "array",
"items": {
"type": "string"
}
}
},
"description": "get_genre response: genre definition, key artists, key tracks; found:false with available_genres otherwise.",
"additionalProperties": true
}get_genre annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}get_playlists — Get Playlists
Advertised read-only
CALL THIS when the user asks where CWI tracks are placed: "what playlists", "where is Diabolique placed". Returns verified playlist placements only.
get_playlists input schema
{
"type": "object",
"properties": {
"artist": {
"type": "string",
"description": "Optional: filter by artist name."
},
"track_id": {
"type": "string",
"description": "Optional: filter by track ID."
}
}
}get_playlists output schema
{
"type": "object",
"required": [
"ok",
"placements",
"count"
],
"properties": {
"ok": {
"type": "boolean"
},
"note": {
"type": "string"
},
"count": {
"type": "integer"
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"placements": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
"label_playlists": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
}
},
"description": "get_playlists response: verified playlist placements only (never pitch status).",
"additionalProperties": true
}get_playlists annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}verify_brief_candidates — Verify Brief Candidates
Advertised read-only
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 data (sync-catalog-data.js, 29 tracks, 27 verified ISRCs). PASS only for a catalog match with a verified ISRC. FLAG for a catalog match without a verified ISRC. DROP for no catalog match (invented or outside the catalog). This tool makes NO Meta API call and holds no Meta key — Spark reasoning is supplied by the caller, the gate is the tool. A match is NOT a license — clearance is direct by Cumulative Web Inc, hp@cumulativeweb.com, one-signature, BMI.
verify_brief_candidates input schema
{
"type": "object",
"required": [
"candidates"
],
"properties": {
"candidates": {
"type": "array",
"items": {
"type": "object",
"required": [
"title"
],
"properties": {
"title": {
"type": "string",
"description": "Proposed track title (required)."
},
"artist": {
"type": "string",
"description": "Proposed artist name."
}
},
"additionalProperties": true
},
"description": "Proposed candidates, up to 50: each {title, artist}. Title matching is case-insensitive and punctuation-insensitive; the artist is echoed, not used for matching."
}
}
}verify_brief_candidates output schema
{
"type": "object",
"required": [
"tool",
"counts",
"decisions",
"verified_shortlist",
"clearance_note"
],
"properties": {
"rule": {
"type": "string"
},
"tool": {
"type": "string"
},
"built": {
"type": "string",
"description": "Build date of this new tool: 2026-10-27 (Meta hackathon new work)."
},
"counts": {
"type": "object",
"properties": {
"drop": {
"type": "integer"
},
"flag": {
"type": "integer"
},
"pass": {
"type": "integer"
},
"proposed": {
"type": "integer"
}
}
},
"_session": {
"type": "object",
"required": [
"session_token",
"step"
],
"properties": {
"step": {
"type": "integer",
"description": "Hop number in this chain (1 = chain start)."
},
"session_token": {
"type": "string",
"description": "Hex session token; echo it as params._session.session_token to continue."
}
},
"description": "Chain session: pass _session.session_token back in the next call to continue the chain.",
"additionalProperties": false
},
"try_next": {
"type": "array",
"items": {
"type": "object",
"required": [
"tool",
"arguments"
],
"properties": {
"tool": {
"type": "string",
"description": "Tool to call next."
},
"purpose": {
"type": "string",
"description": "Why this call is the natural next step."
},
"arguments": {
"type": "object",
"description": "Ready-to-use arguments, pre-populated from the current response.",
"additionalProperties": true
}
},
"description": "Pre-compiled next call: copy `arguments` straight into the next tools/call.",
"additionalProperties": false
},
"description": "Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload."
},
"decisions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"isrc": {
"type": [
"string",
"null"
],
"description": "Verified ISRC from the sync catalog data, or null. Never invented."
},
"decision": {
"type": "string",
"description": "PASS, FLAG, or DROP."
},
"catalog_title": {
"type": [
"string",
"null"
]
},
"catalog_artist": {
"type": [
"string",
"null"
]
},
"proposed_title": {
"type": "string"
},
"decision_reason": {
"type": "string"
},
"isrc_provenance": {
"type": [
"string",
"null"
]
},
"proposed_artist": {
"type": "string"
}
},
"additionalProperties": true
}
},
"gate_source": {
"type": "string"
},
"generated_at": {
"type": "string"
},
"clearance_note": {
"type": "string"
},
"tracks_on_file": {
"type": "integer"
},
"verified_on_file": {
"type": "integer"
},
"verified_shortlist": {
"type": "array",
"items": {
"type": "object",
"properties": {
"isrc": {
"type": "string"
},
"title": {
"type": "string"
},
"artist": {
"type": "string"
}
},
"additionalProperties": true
}
}
},
"description": "verify_brief_candidates response: one deterministic gate decision per candidate plus the verified shortlist.",
"additionalProperties": true
}verify_brief_candidates annotations
{
"readOnlyHint": true,
"idempotentHint": true,
"destructiveHint": false
}Prompts
5 advertised
find-sync-options
Best for agents that need licensable music for a film, TV, or ad scene. Describe the scene and get a workflow: which sync_search queries to run, what editorial descriptors to weigh, and how to present options to a music supervisor. Arguments: scene (required) — e.g. "nightclub fight scene, high energy".
- scene
- Describe the scene needing music, e.g. "nightclub fight scene, high energy". (required)
artist-deep-dive
Best for agents profiling a CWI roster artist. Runs the full deep-dive: get_artist for the profile, get_track on their top songs, and get_featured to see what is hot. Arguments: artist (required) — e.g. "That Boy Hi Hat".
- artist
- Artist name, e.g. "That Boy Hi Hat" or "King Ahkeem". (required)
radio-now-playing
Best for agents that need to know what is live on Cumulative Radio 365 right now. Workflow: call get_radio, parse now-playing track, artist, artwork, listener counts, and present a "tune in" summary. No arguments required.
music-for-moment
Best for agents that need the right track for a moment — workout, coding session, late-night drive, party. Describe the moment and get a workflow: semantic_search for mood, search_catalog for keywords, and how to pick and present the top 3. Arguments: moment (required) — e.g. "late-night coding session".
- moment
- Describe the moment or activity, e.g. "late-night coding session". (required)
release-brief
Best for agents that need the latest CWI release briefing. Workflow: get_release for the fact packet, get_announcements for context, and how to summarize credits, dates, and platform links for a human. No arguments required.
Resources
3 advertised
featured-catalog
This week’s featured tracks: rubric-scored picks with genres, moods, streaming links, and why_featured rationale.
featured-catalog URI
cwi://catalog/featuredradio-schedule
Cumulative Radio 365 program schedule: every slot with track, artist, offset and duration in the deterministic loop.
radio-schedule URI
cwi://radio/schedulegraph-topology
Knowledge-graph topology: node/edge counts plus the top connected nodes by degree.
graph-topology URI
cwi://graph/topology90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-07: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 453 ms
- 95th percentile latency
- 453 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 453 ms · metadata changed · 30 tool(s), 3 resource(s), 5 prompt(s); warnings: Advertises resources/templates/list but does not implement it
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
Claude Code configuration
claude mcp add --transport http cwi-discovery-engine-mcp https://cwi-machine-data.hp-ace.workers.dev/mcpCodex
Codex configuration
codex mcp add cwi-discovery-engine-mcp --url https://cwi-machine-data.hp-ace.workers.dev/mcpCursor
Cursor configuration
{
"mcpServers": {
"cwi-discovery-engine-mcp": {
"url": "https://cwi-machine-data.hp-ace.workers.dev/mcp"
}
}
}Cline
Cline configuration
{
"mcpServers": {
"cwi-discovery-engine-mcp": {
"type": "streamableHttp",
"url": "https://cwi-machine-data.hp-ace.workers.dev/mcp",
"disabled": false
}
}
}VS Code
VS Code configuration
{
"servers": {
"cwi-discovery-engine-mcp": {
"type": "http",
"url": "https://cwi-machine-data.hp-ace.workers.dev/mcp"
}
}
}Gemini CLI
Gemini CLI configuration
gemini mcp add --transport http cwi-discovery-engine-mcp https://cwi-machine-data.hp-ace.workers.dev/mcpClaude Desktop
Claude Desktop configuration
https://cwi-machine-data.hp-ace.workers.dev/mcpWindsurf
Windsurf configuration
{
"mcpServers": {
"cwi-discovery-engine-mcp": {
"serverUrl": "https://cwi-machine-data.hp-ace.workers.dev/mcp"
}
}
}Let your agent find its tools
Find servers like CWI Discovery Engine MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.