# io.github.CumulativeWebInc/cwi-discovery-engine (remote · cwi-machine-data.hp-ace.workers.dev)

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

- Trust score: 79/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `cwi-machine-data.hp-ace.workers.dev`: 79/100 (this document), [markdown](https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data.md), [page](https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data)

## Channel facts

- Endpoint: `https://cwi-machine-data.hp-ace.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 84/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 4385 tokens (~132/item across 33 items; 30 tools + 3 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 30 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 32 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the io.github.CumulativeWebInc/cwi-discovery-engine MCP server?

io.github.CumulativeWebInc/cwi-discovery-engine is a hosted endpoint at https://cwi-machine-data.hp-ace.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

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

### Cursor

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

### VS Code

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

### Codex

```toml
[mcp_servers.cumulativewebinc-cwi-discovery-engine]
url = "https://cwi-machine-data.hp-ace.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cumulativewebinc-cwi-discovery-engine": {
      "type": "remote",
      "url": "https://cwi-machine-data.hp-ace.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cumulativewebinc-cwi-discovery-engine --url 'https://cwi-machine-data.hp-ace.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cumulativewebinc-cwi-discovery-engine:
    url: "https://cwi-machine-data.hp-ace.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "cumulativewebinc-cwi-discovery-engine": {
      "Transport": "http",
      "Url": "https://cwi-machine-data.hp-ace.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add cumulativewebinc-cwi-discovery-engine -t streamable-http -u 'https://cwi-machine-data.hp-ace.workers.dev/mcp'
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 79, 0)

- [security] Stability: 0.97 → pass

### 2026-11-04 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 75, 0)

- [functional] New tool “verify_brief_candidates”

### 2026-10-26 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (30)

### `find_tracks_for_brief` (~241 tokens)

Find Tracks for a Brief

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

Input parameters:

- `brief` (string, required): Natural-language music brief, e.g. "tense instrumental for a heist scene". Truncated at 500 characters.
- `explicit` (boolean): true = explicit only, false = non-explicit only. Omit for all.
- `limit` (number): Max tracks to return, 1-5 (default 3).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `brief` (string)
- `clearance_summary` (string): Plain-language clearance status for the matched tracks: who controls master+publishing, one-signature terms, PRO.
- `count` (integer)
- `generated_at` (string)
- `licensing_disclaimer` (string): States that a match is not a license grant.
- `next_steps` (array): Concrete actions: submit_sync_brief with the brief, contact email, license terms URL.
- `tokens` (array)
- `tracks` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `search_catalog` (~141 tokens)

Search Catalog

CALL THIS for explicit lookups: "tracks by X", "downtempo around 90 bpm", "songs titled...". Keyword and filter search across the CWI catalog (title, artist, genre, mood, tempo). Use semantic_search instead if the user describes a feeling. Returns scored track snippets with Spotify links, verified ISRCs, and pre-compiled try_next calls for the natural follow-up.

Input parameters:

- `limit` (number): Max tracks to return, 1-10 (default 5).
- `q` (string, required): Search keywords, e.g. "cyberpunk rap" or "dark cinematic". Truncated at 500 characters.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `generated_at` (string)
- `limit` (integer)
- `new_release_spotlight` (object): Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.
- `query` (string)
- `results` (array)
- `tokens` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_track` (~114 tokens)

Get Track Details

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.

Input parameters:

- `id_or_title` (string, required): Track title (exact or partial) or a Spotify track ID / open.spotify.com URL.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `album` (string|null)
- `apple_music_url` (string)
- `artist` (string)
- `artist_mbid` (string|null): MusicBrainz artist MBID.
- `artwork_url` (string|null)
- `contexts` (array)
- `credits` (object|null)
- `description` (string): 150-300 word NLP prose (Whisper-derived where flagged; not proofread).
- `engineer` (string|null)
- `featured` (boolean)
- `genres` (array)
- `graph_node` (string)
- `isrc` (string|null)
- `label` (string|null)
- `mbid` (string|null): MusicBrainz recording MBID.
- `moods` (array)
- `presave_url` (string|null)
- `producers` (array)
- `related_nodes` (array): Up to 8 connected knowledge-graph node IDs.
- `release_date` (string|null): Original commercial release date (YYYY-MM-DD).
- `scenes` (array)
- `signature` (object|null): That Boy Hi Hat flow-architecture signature block (present on his tracks).
- `sounds_like_lanes` (array)
- `spotify_url` (string)
- `streaming_urls` (object|null)
- `studio` (string|null)
- `summary_markdown` (string): Compact markdown: title, ISRC/UPC, studio, genres/moods, one-line sync clearance.
- `title` (string)
- `track_id` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `upc` (string|null)
- `use_cases` (array)

### `get_artist` (~106 tokens)

Get Artist Profile

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.

Input parameters:

- `name` (string, required): Artist name, e.g. "That Boy Hi Hat".

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `artist` (string)
- `related_nodes` (array): Up to 8 connected knowledge-graph node IDs.
- `track_count` (integer)
- `tracks` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `sync_search` (~211 tokens)

Search Sync Catalog

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.

Input parameters:

- `bpm_max` (number): Maximum BPM (inclusive).
- `bpm_min` (number): Minimum BPM (inclusive).
- `explicit` (boolean): true = explicit only, false = non-explicit only. Omit for all.
- `mood` (string): Mood filter, matched against moods + energy words, e.g. "aggressive".
- `q` (string, required): Sync query, e.g. "club scene" or "dark aggressive". Truncated at 500 characters.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `descriptor_provenance` (string)
- `filters_applied` (object)
- `generated_at` (string)
- `license_block` (string): Markdown licensing summary for the top hit: ISRC, rights holders, clearance terms, contact.
- `query` (string)
- `results` (array)
- `tokens` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `semantic_search` (~95 tokens)

Semantic Music Search

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

Input parameters:

- `limit` (number): Max results, 1-20 (default 5).
- `q` (string, required): Natural-language music query, e.g. "dark cyberpunk rap for a film scene". Truncated at 500 characters.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `dim` (integer)
- `fallback` (boolean)
- `fallback_note` (string)
- `generated_at` (string)
- `limit` (integer)
- `method` (string): cosine:<model> or fallback:keyword.
- `model` (string)
- `query` (string)
- `results` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_graph` (~74 tokens)

Get Catalog Graph

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

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `full_graph` (string)
- `generated_at` (string)
- `source` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_release` (~110 tokens)

Get Release Info

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.

Input parameters:

- `id` (string): Release id, e.g. "cyberpunk-2027". Omit for the latest release.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `found` (boolean)
- `id` (string)
- `known_releases` (array)
- `new_release_spotlight` (object): Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.
- `packet` (object): Fact packet: facts list of {claim, evidence{source, observed}, tier}.
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_radio` (~86 tokens)

Get Radio Status

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.

Input parameters:

- `include` (string): Optional comma-separated sections to include: "now_playing", "listeners", "stream". Omit or pass "all" for everything. Unknown values are ignored.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `generated_at` (string)
- `listeners` (object)
- `now_playing` (object)
- `proof_of_airplay` (object)
- `station` (string)
- `station_url` (string)
- `stream` (object)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_announcements` (~113 tokens)

Get Announcements

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

Input parameters:

- `category` (string): Optional filter: "releases", "news", or "events". Omit for all categories.
- `limit` (number): Max announcements to return, 1-50 (default 10).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `announcements` (array)
- `category` (string)
- `count` (integer)
- `data_updated_at` (string|null)
- `generated_at` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_featured` (~75 tokens)

Get Featured Tracks

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.

Input parameters:

- `limit` (number): Max tracks to return, 1-20 (default 10).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `data_updated_at` (string|null)
- `featured` (array)
- `generated_at` (string)
- `new_release_spotlight` (object): Active pre-release spotlight: title, artist, drop date, presave URL, ISRC.
- `rotation` (string|null)
- `rotation_raw` (string|null)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_up_next` (~63 tokens)

Get Up Next on Radio

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.

Input parameters:

- `count` (number): Number of upcoming tracks to return, 1-10 (default 5).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `generated_at` (string)
- `note` (string)
- `now_playing` (object)
- `program_version` (string|null)
- `station` (string)
- `stream_url` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `up_next` (array)

### `get_schedule` (~101 tokens)

Get Radio Schedule

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

Input parameters:

- `date` (string): Date for the schedule in YYYY-MM-DD format. Defaults to today (UTC).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `date` (string)
- `generated_at` (string)
- `note` (string)
- `period_seconds` (number|null)
- `program_version` (string|null)
- `slot_count` (integer)
- `slots` (array)
- `station` (string)
- `stream_url` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `request_song` (~184 tokens)

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).

Input parameters:

- `artist` (string, required): Artist name.
- `dedication` (string): Optional: who this request is dedicated to.
- `reason` (string): Optional: why you want to hear this track.
- `requested_by` (string, required): Your name or agent identity (used for rate limiting).
- `track_title` (string, required): Title of the track you want to hear.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `artist` (string)
- `estimated_air_in_minutes` (integer)
- `ok` (boolean)
- `queue_position` (integer)
- `request_id` (integer|null)
- `requested_at` (string)
- `requested_by` (string)
- `review` (string)
- `status` (string)
- `track_title` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `submit_for_airplay` (~188 tokens)

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).

Input parameters:

- `artist_name` (string, required): Artist name.
- `audio_url` (string, required): Streamable URL to the track audio (required for review).
- `contact` (string, required): Email or social handle for follow-up.
- `genre` (string): Genre of the track.
- `message` (string): Optional pitch: why this track fits Radio 365.
- `track_title` (string, required): Track title.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `artist_name` (string)
- `genre` (string|null)
- `ok` (boolean)
- `review_note` (string)
- `status` (string)
- `submission_id` (integer|null)
- `submitted_at` (string)
- `track_title` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `what_happens_next` (string)

### `get_requests` (~133 tokens)

Get Song Requests

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

Input parameters:

- `limit` (number): Max requests to return, 1-20 (default 10).
- `status` (string): Filter by status: "pending" (awaiting review), "played" (aired), "all". Default "pending".

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `generated_at` (string)
- `note` (string)
- `pending_count` (integer)
- `requests` (array)
- `station` (string)
- `status_filter` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `submit_sync_brief` (~304 tokens)

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).

Input parameters:

- `budget_range` (string): Optional budget range (e.g. "$1k-5k", "$10k+").
- `contact` (string, required): Email for follow-up (required).
- `deadline` (string): Optional deadline in YYYY-MM-DD format.
- `description` (string): Optional: more detail about the project or scene.
- `mood` (string, required): Mood/energy needed (e.g. "dark aggressive", "uplifting anthemic").
- `project_name` (string): Optional project/film/show name.
- `scene_type` (string, required): Type of scene needing music (e.g. "car chase", "romantic montage").

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `brief_id` (integer|null)
- `budget_range` (string|null)
- `deadline` (string|null)
- `license_block` (string): Markdown licensing summary: rights holders, clearance terms, contact.
- `mood` (string)
- `ok` (boolean)
- `project_name` (string|null)
- `rights_note` (string)
- `scene_type` (string)
- `status` (string)
- `submitted_at` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `what_happens_next` (string)

### `pitch_for_playlist` (~197 tokens)

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).

Input parameters:

- `artist` (string, required): Artist name.
- `contact` (string): Optional: email for follow-up.
- `curator` (string): Optional: curator name or handle.
- `playlist_name` (string): Optional: target playlist name.
- `track_title` (string, required): Title of the track you are pitching.
- `why_fit` (string, required): Why this track fits the playlist (required).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `artist` (string)
- `curator` (string|null)
- `note` (string)
- `ok` (boolean)
- `pitch_id` (integer|null)
- `playlist_name` (string|null)
- `receipt` (object): Confirmation receipt; id is the real intake row id.
- `review` (string)
- `status` (string)
- `submitted_at` (string)
- `track_data` (object|null)
- `track_title` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `why_fit` (string)

### `nominate_featured` (~165 tokens)

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).

Input parameters:

- `artist` (string, required): Artist name.
- `nominated_by` (string, required): Your name or agent identity (required).
- `reason` (string, required): Why this track deserves the featured rotation (required).
- `track_title` (string, required): Title of the track you are nominating.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `artist` (string)
- `graph_node` (string|null)
- `in_current_rotation` (boolean)
- `nominated_by` (string)
- `nomination_id` (integer|null)
- `ok` (boolean)
- `queue_position` (integer)
- `receipt` (object): Confirmation receipt; id is the real intake row id.
- `review` (string)
- `rubric_note` (string)
- `rubric_score` (number|null)
- `status` (string)
- `submitted_at` (string)
- `track_title` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_recommendations` (~254 tokens)

Get Music Recommendations

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

Input parameters:

- `count` (number): Number of recommendations, 1-10 (default 5).
- `genre_filter` (string): Optional genre filter (e.g. "trap", "afrobeats", "rap rock").
- `vibe_description` (string, required): Describe the vibe/mood you want music for.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `generated_at` (string)
- `genre_filter` (string|null)
- `method` (string)
- `new_release_spotlight` (object|null)
- `note` (string)
- `recommendations` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `vibe_description` (string)

### `get_events` (~83 tokens)

Get Events

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

Input parameters:

- `upcoming_only` (boolean): Only show upcoming events (default true). Set false to see all.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `events` (array)
- `generated_at` (string)
- `note` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `upcoming_only` (boolean)

### `rsvp` (~157 tokens)

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).

Input parameters:

- `contact` (string, required): Email for confirmation (required).
- `event_id` (string, required): Event ID from get_events (required).
- `name` (string, required): Your name (required).
- `plus_ones` (number): Number of additional guests (default 0).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `confirmation` (string)
- `event_id` (string)
- `event_title` (string)
- `name` (string)
- `ok` (boolean)
- `plus_ones` (integer)
- `rsvp_at` (string)
- `rsvp_id` (integer|null)
- `status` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_label` (~52 tokens)

Get Label Profile

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.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `label` (object)
- `ok` (boolean)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_sync_catalog` (~139 tokens)

Get Sync Catalog

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

Input parameters:

- `genre` (string): Filter by genre, e.g. "post-trap futurism".
- `mood` (string): Filter by mood, e.g. "dark", "energetic".

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `note` (string)
- `ok` (boolean)
- `tracks` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_lyrics` (~64 tokens)

Get Lyrics

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

Input parameters:

- `track_id` (string, required): Track ID from get_track or search_catalog (required).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `found` (boolean)
- `lyrics` (object)
- `note` (string)
- `ok` (boolean)
- `track_id` (string)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_press_kit` (~68 tokens)

Get Press Kit

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

Input parameters:

- `artist` (string): Optional: specific artist name for their press bio.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `ok` (boolean)
- `press_kit` (object)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_videos` (~76 tokens)

Get Videos

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

Input parameters:

- `artist` (string): Optional: filter by artist name.
- `type` (string): Optional: filter by type (trailer, music-video, visualizer, live).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `ok` (boolean)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `videos` (array)

### `get_genre` (~100 tokens)

Get Genre Info

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.

Input parameters:

- `genre` (string, required): Genre name, e.g. "post-trap futurism" (required).

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `available_genres` (array)
- `found` (boolean)
- `genre` (object|string)
- `ok` (boolean)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `get_playlists` (~67 tokens)

Get Playlists

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

Input parameters:

- `artist` (string): Optional: filter by artist name.
- `track_id` (string): Optional: filter by track ID.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `count` (integer)
- `label_playlists` (array)
- `note` (string)
- `ok` (boolean)
- `placements` (array)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.

### `verify_brief_candidates` (~220 tokens)

Verify Brief Candidates

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

Input parameters:

- `candidates` (array, required): Proposed candidates, up to 50: each {title, artist}. Title matching is case-insensitive and punctuation-insensitive; the artist is echoed, not used for matching.

Output parameters:

- `_session` (object): Chain session: pass _session.session_token back in the next call to continue the chain.
- `built` (string): Build date of this new tool: 2026-10-27 (Meta hackathon new work).
- `clearance_note` (string)
- `counts` (object)
- `decisions` (array)
- `gate_source` (string)
- `generated_at` (string)
- `rule` (string)
- `tool` (string)
- `tracks_on_file` (integer)
- `try_next` (array): Suggested follow-up calls, each a pre-compiled {tool, arguments, purpose} payload.
- `verified_on_file` (integer)
- `verified_shortlist` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data#diagnostics

## Score history

- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 77
- 2026-10-31: 77
- 2026-10-30: 76
- 2026-10-29: 76
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 75
- 2026-10-25: 74
- 2026-10-24: 74
- 2026-10-23: 73
- 2026-10-22: 73
- 2026-10-21: 72
- 2026-10-20: 72
- 2026-10-19: 72
- 2026-10-18: 71
- 2026-10-17: 71
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 69
- 2026-10-13: 69
- 2026-10-12: 68
- 2026-10-10: 67
- 2026-10-06: 58

## Common questions

### What is the io.github.CumulativeWebInc/cwi-discovery-engine MCP server?

io.github.CumulativeWebInc/cwi-discovery-engine is an MCP server listed in the public MCP registry as io.github.CumulativeWebInc/cwi-discovery-engine. CWI Discovery Engine: 29-tool music catalog MCP, search, sync, Radio 365 live, chaining. This page covers its hosted endpoint (https://cwi-machine-data.hp-ace.workers.dev/mcp).

### Is the io.github.CumulativeWebInc/cwi-discovery-engine MCP server safe to use?

io.github.CumulativeWebInc/cwi-discovery-engine scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.CumulativeWebInc/cwi-discovery-engine MCP server expose?

io.github.CumulativeWebInc/cwi-discovery-engine exposes 30 tools: find_tracks_for_brief, search_catalog, get_track, get_artist, sync_search, and 25 more. Their descriptions and schemas cost roughly 3,981 tokens of context every time the server is loaded.

### Does the io.github.CumulativeWebInc/cwi-discovery-engine MCP server require authentication?

No. We connected to io.github.CumulativeWebInc/cwi-discovery-engine without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.CumulativeWebInc/cwi-discovery-engine MCP server still maintained?

io.github.CumulativeWebInc/cwi-discovery-engine is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the io.github.CumulativeWebInc/cwi-discovery-engine MCP server?

VerifyMCP ran 13 checks on io.github.CumulativeWebInc/cwi-discovery-engine, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://cwi-machine-data.hp-ace.workers.dev/mcp
- Repository: https://github.com/CumulativeWebInc/cwi-learn
- Website: https://cumulativeweb.com/
- Changelog RSS feed: https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data.xml
- Changelog JSON feed: https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data.json
- HTML version of this page: https://verifymcp.io/servers/cumulativewebinc-cwi-discovery-engine/cwi-machine-data