app.aiponge/mcp

Est-ce que app.aiponge/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « app.aiponge/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 23 outils

• browse_books≈ 452 tokens

  Browse / search / discover / find books in the shared aiponge library catalog (not just the user's own — for those use list_books). "Find me a book about gratitude", "what books are there on sleep?", "browse the library". Optionally filter by `search` text or `typeId`. Searches all languages by default. Returns matching books with their ids — then use read_book to read one, or play_audiobook to listen.

  Paramètres, retour & exemple (6)

  Paramètres

  • limit · integer · optionnel
  • cursor · string · optionnel
  • offset · integer · optionnel
  • search · string · optionnel
    Free-text search across the catalog (title/description).
  • typeId · string · optionnel
    Optional book type to filter by, e.g. 'wisdom', 'guide', 'journal'.
  • language · string · optionnel
    ISO language code to scope results to, e.g. 'en'. Omit to search ALL languages (default).

  Exemple d'appel

  {"name": "browse_books", "arguments": {"limit": 1, "cursor": "texte", "offset": 1, "search": "texte", "typeId": "texte", "language": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"books": [], "total": 1, "hasMore": true, "nextCursor": "texte"}}

• compose_entry≈ 443 tokens

  THE DEFAULT WAY TO SAVE A REFLECTION OR JOURNAL ENTRY. Use this — NOT create_entry — for any request like "save this as a journal entry", "journal this", "add a journal entry", "save my reflection", "put this in my diary", "write this down". It opens an in-chat journal composer PRE-FILLED with a draft you write from the conversation, for the user to edit and save. It does NOT persist on its own; the user reviews and saves from the panel (Save then calls create_entry). Pass `draft` as your best draft of their entry (or "" for a blank composer). In clients without panels, show the draft and wait for explicit confirmation, then use save_entry with a stable operationId.

  Paramètres, retour & exemple (3)

  Paramètres

  • draft · string · optionnel
    Draft entry text written from the conversation for the user to edit. Empty string opens a blank composer.
  • suggestedMood · string · optionnel
    Optional mood/context suggestion to pre-fill.
  • suggestedTags · array · optionnel
    Optional tag suggestions to pre-fill.

  Exemple d'appel

  {"name": "compose_entry", "arguments": {"draft": "texte", "suggestedMood": "texte", "suggestedTags": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"draft": "texte", "suggestedMood": "texte", "suggestedTags": []}}

• correct_insight≈ 333 tokens

  Record the user's explicit correction to a specific inferred dimension/value they have seen in aiponge. Do not invent a dimension or value, and do not treat this as a diagnosis. Use only when the user confirms the correction. The backend validates the canonical dimension and reaction.

  Paramètres, retour & exemple (5)

  Paramètres

  • value · string · requis
  • freeText · string · optionnel
  • confirmed · boolean · requis
  • dimension · string · requis · preferredThemes | preferredMoods | approachGentlyThemes | userArticulatedLearnings | wisdomIntegrated | wisdomInFlux | coherenceValues | coherenceBeliefs
  • correction · string · requis · affirmed | partial | rejected | dismissed | rephrased | not_me | not_quite | wrong_phrasing

  Exemple d'appel

  {"name": "correct_insight", "arguments": {"value": "texte", "confirmed": true, "dimension": "preferredThemes", "correction": "affirmed"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_entry≈ 853 tokens

  Persist a journal entry DIRECTLY to the journal, with NO review step. This is the silent/import-only path — for an ordinary chat request like "save this as a journal entry" / "journal this" / "add a journal entry", do NOT use this; use `compose_entry`, which opens an editable composer the user confirms. Reach for `create_entry` ONLY for silent/automated saves: structured memory-inventory imports, or when the user explicitly asks to save without reviewing. `content` is the only required field. For imports, include entryDate, entryDateDisplay, location, sourceMemoryId, sourceSection, sourceTitle, sourceType, dateConfidence, sensitivity, tags, and metadata when known. Returns the saved entry including its `id`, which can then be used to turn the entry into a song linked to it (the track generator accepts a journal entry id).

  Paramètres, retour & exemple (15)

  Paramètres

  • tags · array · optionnel
    Optional tags; lowercase preferred.
  • type · string · optionnel
    Optional entry type, e.g. 'reflection' (default), 'note', 'insight'. Usually omit.
  • content · string · requis
    The reflection text to save as a journal entry.
  • location · string · optionnel
    Free-text location, e.g. "Marseille, France".
  • metadata · object · optionnel
    Flexible JSON metadata for import/review context.
  • entryDate · string · optionnel
    ISO 8601 date or datetime, e.g. 1973-06-01 or 1989-11-30T10:00:00Z.
  • sourceType · string · optionnel
    Suggested values: book_memory, journal_import, manual_entry, song_reflection.
  • moodContext · string · optionnel
    Optional short note on the mood/context. Usually omit.
  • operationId · string · optionnel
    Stable operation ID for a panel save retry.
  • sensitivity · string · optionnel
    Suggested values: normal, private, sensitive, very_sensitive.
  • sourceTitle · string · optionnel
    Human-readable source title.
  • sourceSection · string · optionnel
    Book/source section, e.g. "L Accident".
  • dateConfidence · string · optionnel
    Suggested values: high, medium, low.
  • sourceMemoryId · string · optionnel
    External memory inventory id, e.g. M021.
  • entryDateDisplay · string · optionnel
    Human-readable date label, e.g. "ete 1973" or "date approximative".

  Exemple d'appel

  {"name": "create_entry", "arguments": {"content": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• generate_track≈ 1851 tokens

  Create / make / write / generate a SONG, a TRACK, or a piece of MUSIC for the user from a topic (e.g. "a calm morning walk", "write me a song about my mom", "make me some music about the sea"). This is THE tool for any "create/make/write a song|track|music" request. Provide EITHER a `topic` OR an `entryId` — do NOT ask the user for, or invent, a genre / mood / vocal style / language. The user's saved audio preferences are applied automatically, so the optional style fields are advanced overrides best left unset. For an explicit song request, set `audioType:"song"` so a saved spoken-audio default does not change the requested format. • FROM A JOURNAL ENTRY: to "turn my last entry into a song" / "make a track for this entry", pass `entryId` (from create_entry's result, or resolved via list_entries / search_entries). This links the track to that entry and uses its content for the lyrics — `topic` is then optional. • CONTENT FORMAT: use "song" for music with lyrics and affirmations, or "atmosphere" for an instrumental / ambient / focus / sleep soundscape with no lyrics. Spoken reflection and guided narration are unavailable through the current music provider. Explain that limitation instead of starting a reflection or guided request. • PROGRESS: takes ~1–3 minutes. By DEFAULT it returns immediately and a live progress panel shows the track filling in, then turns into the player — so leave `wait` unset and just tell the user it is composing (no need to poll; the panel does it). If the user asks later, get_generation_status checks progress and play_track plays a finished track. Only pass `wait:true` for scripted/non-interactive callers that must block ~1–3 minutes and get the finished play link back in one call.

  Paramètres, retour & exemple (12)

  Paramètres

  • mood · string · optionnel
    Optional style override. Usually omit — defaults come from the user's saved preferences.
  • wait · boolean · optionnel
    Leave this UNSET (default false): the tool returns immediately and a live progress panel shows the track filling in, then becomes the player — the best in-chat experience. Set true ONLY for scripted / non-interactive callers that need to block ~1–3 min and get the finished play link back in one call (no progress is shown while blocking).
  • genre · string · optionnel
    Optional style override. Usually omit — the user's saved audio preferences supply this.
  • topic · string · optionnel
    What the song / track should be about. Optional ONLY when you pass `entryId` (the entry supplies the content); otherwise this is required.
  • entryId · string · optionnel
    Generate the track FROM an existing journal entry: links the new track to that entry and uses the entry's content for the lyrics. Pass the entry's UUID — from create_entry's result, or resolved via list_entries / search_entries. When set, `topic` is optional.
  • language · string · optionnel
    Optional ISO 639-1 override. Usually omit — defaults to the user's saved language.
  • songGoal · string · optionnel · reflect | guide | embellish | tell | reframe | explore | elevate | explain
    Canonical song mode; defaults to 'mirror' when omitted. Use this instead of lyricsRegister. Available modes: mirror, coach, poet, storyteller, reframer, explorer, mythic, explain, tribute. - 'mirror' (default): a song that REFLECTS THE LISTENER's inner world — feelings, memories, or an experience they are inside. Examples: "a song about how I keep building walls around myself", "a song about my mother", "a song about feeling stuck", "a song about my morning walk". - 'tribute': a song ABOUT AN EXTERNAL SUBJECT — a brand, organization, place, craft, public figure, or idea — that preserves the subject's concrete, identifying substance. Examples: "a song about [Company Name]", "a song about the city of Lisbon", "a song about the craft of programming", "a song honoring my late grandfather Marcel". Strong tribute signals: a proper noun, a URL, a description of an entity rather than a feeling, words like "tribute", "about [name]", "honoring", "for [name]". - 'explain': a song that makes an idea or reflection clearer through a singable narrative, without turning into a lecture or advice. When the request CLEARLY matches one mode, set the field and proceed. When the request is genuinely AMBIGUOUS between mirror and tribute (e.g. "a song about my work" — is 'my work' the listener's relationship with it, or an external thing?), ASK THE USER ONE SHORT QUESTION before calling: "Should this be a song reflecting your experience, or a song about that as a subject?" Default to 'mirror' only when the request describes a personal feeling or experience without any external named entity.
  • audioType · string · optionnel · song | instrumental
    Set song explicitly for a song request; omit only when the user wants their saved default content type. 'atmosphere' = an instrumental / ambient / focus / sleep soundscape with no lyrics; 'song' = music with lyrics (an affirmation is a song). The legacy 'guided' and 'reflection' values are unavailable through the current music provider.
  • operationId · string · optionnel
    Caller-owned UUID for this creation. Reuse it only for a retry of the same request, including after reconnecting.
  • vocalGender · string · optionnel · f | m
    Optional override. Usually omit — defaults to the user's saved vocal preference.
  • lyricsRegister · string · optionnel · wellness | honor
    Legacy alias; prefer songGoal.
  • audioPreferenceProfileId · string · optionnel
    Optional ID of one of the user's saved sound profiles. Call list_audio_preference_profiles first when the user asks to use a named saved sound; this applies that profile only to this song.

  Exemple d'appel

  {"name": "generate_track", "arguments": {"mood": "texte", "wait": true, "genre": "texte", "topic": "texte", "entryId": "texte", "language": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"phase": "texte", "title": "texte", "topic": "texte", "status": "texte", "trackId": "texte", "audioUrl": "texte", "duration": 1, "requestId": "texte", "artworkUrl": "texte", "displayName": "texte", "errorMessage": "texte", "percentComplete": 1}}

• get_capabilities≈ 784 tokens

  Return the canonical aiponge MCP tool map, workflow order, account/role requirements, and UI panel capabilities. Use only to choose tools for supported reflection, journal, music, or book requests. Do not call this or any aiponge tool for account deletion, unrelated local search such as restaurants, or invitations and group membership. For account deletion, direct the user to aiponge account settings or support. For invitations or group membership, direct the user to the aiponge App. Handle unrelated requests without aiponge. These exclusions are already known; do not look them up.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_capabilities", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"server": {}, "workflows": [], "toolCounts": {}, "accessPolicy": {}, "capabilities": {}}}

• get_entry≈ 176 tokens

  Open / read the full text of ONE specific journal entry by its id. Resolve the id via list_entries or search_entries first; never invent an entry id.

  Paramètres, retour & exemple (1)

  Paramètres

  • entryId · string · requis
    The id of the journal entry to fetch (from list_entries).

  Exemple d'appel

  {"name": "get_entry", "arguments": {"entryId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_generation_status≈ 358 tokens

  Check on a song/track/music that is still being generated — "is my song ready?", "how is it coming along?". Takes the requestId returned by generate_track. Returns progress while generating, a play link when complete, or the failure reason. When complete, you can also call play_track with the returned trackId. When polling, wait at least 30 seconds between calls — generation takes 1–3 minutes, so checking more often than every 30 seconds just wastes calls and never returns sooner.

  Paramètres, retour & exemple (1)

  Paramètres

  • requestId · string · requis
    The requestId returned by generate_track.

  Exemple d'appel

  {"name": "get_generation_status", "arguments": {"requestId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"phase": "texte", "title": "texte", "topic": "texte", "status": "texte", "trackId": "texte", "audioUrl": "texte", "duration": 1, "requestId": "texte", "artworkUrl": "texte", "displayName": "texte", "errorMessage": "texte", "percentComplete": 1}}

• get_insights≈ 253 tokens

  Surface what aiponge has NOTICED about the user: the observations, recurring patterns, and wellness signal drawn from their self-model, inferred from their reflections. Read-only. Use it when the user asks "what has aiponge learned about me?", "what patterns do you see in me?", "what are my themes?", "how am I doing?", or to understand the user before suggesting actions. This is the INFERRED picture, not a diagnosis; for the user's explicitly-set settings (audio preferences, language, account) use get_profile instead. Returns empty sections for a new user with little history.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_insights", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_profile≈ 244 tokens

  Show the user's account profile and saved settings: "what's on my profile?", "what language am I set to?", "my account settings". Returns account details, profile, general preferences, and activity counts, including saved song genre, vocals, and instruments when configured. Unset preference fields may be absent; do not infer values for missing fields. Use list_audio_preference_profiles to select a named saved sound for generation. Read-only. To learn what aiponge has noticed from reflections, including themes and patterns, use get_insights instead.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_profile", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_track≈ 230 tokens

  Read the lyrics, source entry ID and context of a saved song. Use a real trackId from list_tracks or generation. Does not start playback.

  Paramètres, retour & exemple (1)

  Paramètres

  • trackId · string · requis

  Exemple d'appel

  {"name": "get_track", "arguments": {"trackId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"track": {}}}

• get_usage≈ 303 tokens

  Read available account allowances and reset time before planning creation. This is advisory; the server still reserves usage atomically. Unavailable counters are identified explicitly; do not assume their remaining allowance.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_usage", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"allowances": [], "unavailableFeatures": []}}

• list_audio_preference_profiles≈ 154 tokens

  List the user's saved song sound profiles, including each profile ID and label. Use this before generate_track when the user asks to create a song with a named saved sound. Read-only.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_audio_preference_profiles", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_books≈ 319 tokens

  Show / list the user's OWN books — "what books do I have?", "my library", "my books". Returns only the books they own or created, NOT the shared aiponge catalog. To discover or search the wider aiponge book catalog, use browse_books instead.

  Paramètres, retour & exemple (3)

  Paramètres

  • limit · integer · optionnel
  • cursor · string · optionnel
  • offset · integer · optionnel

  Exemple d'appel

  {"name": "list_books", "arguments": {"limit": 1, "cursor": "texte", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"books": [], "total": 1, "hasMore": true, "nextCursor": "texte"}}

• list_generations≈ 150 tokens

  Find the account's active song generation requests after reconnecting or losing a requestId. Inspect them before retrying generation. Completed songs can be found with list_tracks.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_generations", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_tracks≈ 598 tokens

  Show / list / browse the user's songs — "what songs do I have?", "show me my music", "my tracks", "my library", "my playlist of songs". Returns the user's private music tracks. Each item includes its `title`, `themes` (canonical topic tags the track was generated around, e.g. ["travel", "solitude"]), and `inspiration` (a short hint about what the song is ABOUT, derived from the original generation prompt). Also use this to RESOLVE a play request to a specific track: for "play something about Berlin" or "play the song about my mom", match against ALL THREE fields — not just `title` — and pick the row whose themes / inspiration / title best fits the request, then hand its id to play_track. If several rows plausibly match, list them and ask the user which one rather than guessing. The tracks render as an interactive player panel the user can see and play from directly (the per-track fields are in structuredContent) — after calling this, reply with at most a one-line intro and do NOT re-list the tracks in text; the panel already shows them.

  Paramètres, retour & exemple (4)

  Paramètres

  • limit · integer · optionnel
  • query · string · optionnel
    Search saved songs by title, themes or inspiration.
  • cursor · string · optionnel
    Use nextCursor from the preceding result; do not invent it.
  • offset · integer · optionnel

  Exemple d'appel

  {"name": "list_tracks", "arguments": {"limit": 1, "query": "texte", "cursor": "texte", "offset": 1}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"total": 1, "tracks": [], "hasMore": true, "nextCursor": "texte"}}

• play_audiobook≈ 392 tokens

  Play / listen to a book as an audiobook — its chapters narrated as TTS audio, in order, with clickable stream links. "Read this book aloud", "play the audiobook", "I want to listen to a book". Resolve the bookId via browse_books or list_books first. Many catalog books are narrated; if a book isn't, this says so (read its text with read_book instead).

  Paramètres, retour & exemple (3)

  Paramètres

  • bookId · string · requis
    The id of the book to read (from browse_books or list_books).
  • chapterLimit · integer · optionnel
    Bound the chapters returned. Omit with chapterOffset for the full interactive book.
  • chapterOffset · integer · optionnel
    Zero-based first chapter to read.

  Exemple d'appel

  {"name": "play_audiobook", "arguments": {"bookId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"title": "texte", "segments": [], "totalSec": 1}}

• play_track≈ 324 tokens

  Play / listen to / put on ONE specific song the user already has — returns a fresh, clickable stream link for that track by its id. The user normally refers to a track by NAME, not id: when the requested title is approximate, partial, or possibly misspelled, FIRST call list_tracks (request the full library, e.g. limit 100), pick the closest matching title, then call this tool with its id. If several tracks plausibly match, list them and ask the user which one rather than guessing. Never invent a track id. (To browse or show the whole library, use list_tracks; to create a new song, use generate_track.)

  Paramètres, retour & exemple (1)

  Paramètres

  • trackId · string · requis

  Exemple d'appel

  {"name": "play_track", "arguments": {"trackId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"title": "texte", "trackId": "texte", "audioUrl": "texte", "duration": 1, "artworkUrl": "texte", "displayName": "texte"}}

• read_book≈ 498 tokens

  Read / open a book's text content — its chapters and the prose of each — so you can summarize, quote, or discuss it. "Read me that book", "what does the book say?", "summarize this book". Resolve the bookId via browse_books or list_books first. Set chapterOffset and chapterLimit for a bounded chapter read. To LISTEN to it as narrated audio instead, use play_audiobook.

  Paramètres, retour & exemple (3)

  Paramètres

  • bookId · string · requis
    The id of the book to read (from browse_books or list_books).
  • chapterLimit · integer · optionnel
    Bound the chapters returned. Omit with chapterOffset for the full interactive book.
  • chapterOffset · integer · optionnel
    Zero-based first chapter to read.

  Exemple d'appel

  {"name": "read_book", "arguments": {"bookId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"book": {}, "chapterPage": {}}}

• save_entry≈ 362 tokens

  For clients without a journal panel: save the exact reflection the user has reviewed and explicitly confirmed. Never set confirmed from silence or inferred intent. Use compose_entry to prepare a draft; show it to the user, then save only after confirmation. Reuse operationId for retries of the same text. In interactive ChatGPT, prefer the journal panel Save action.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • content · string · requis
  • confirmed · boolean · requis
  • moodContext · string · optionnel
  • operationId · string · requis

  Exemple d'appel

  {"name": "save_entry", "arguments": {"content": "texte", "confirmed": true, "operationId": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"saved": true, "entryId": "texte"}}

• search_entries≈ 609 tokens

  Search the user-owned journal by words in any supported language, tag, personal date, or import source. Returns matching entry IDs and short excerpts. Use get_entry for full text. Follow nextCursor with identical filters until hasMore is false before claiming there are no older matches. total counts only this response. Journal resolution errors do not broaden the search to other books.

  Paramètres, retour & exemple (12)

  Paramètres

  • tags · array · optionnel
  • limit · integer · optionnel
  • query · string · optionnel
  • cursor · string · optionnel
    Continuation from a previous search; keep the same filters.
  • offset · integer · optionnel
  • toDate · string · optionnel
  • fromDate · string · optionnel
  • location · string · optionnel
  • sourceType · string · optionnel
  • sensitivity · string · optionnel
  • sourceMemoryId · string · optionnel
  • includeAllBooks · boolean · optionnel
    Default false: return only the user's own journal entries (their personal Journal book). Set true to return entries from ALL their books, including book-derived content (insights, excerpts, exercises generated from books in their library).

  Exemple d'appel

  {"name": "search_entries", "arguments": {"tags": [], "limit": 1, "query": "texte", "cursor": "texte", "offset": 1, "toDate": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"scope": "texte", "total": 1, "entries": [], "hasMore": true, "scanned": 1, "nextCursor": "texte", "totalIsExact": true, "journalExists": true, "duplicateSourceMemoryId": true}}

• submit_track_feedback≈ 286 tokens

  Record only explicit user feedback on a saved song: understood, partial or missed. Never infer recognition or helpfulness from playback. Replaces the user's previous feedback for this song. Resolve trackId first.

  Paramètres, retour & exemple (5)

  Paramètres

  • context · string · optionnel
  • trackId · string · requis
  • confirmed · boolean · requis
  • resonance · string · requis · understood | partial | missed
  • wasHelpful · boolean · requis

  Exemple d'appel

  {"name": "submit_track_feedback", "arguments": {"trackId": "texte", "confirmed": true, "resonance": "understood", "wasHelpful": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• update_audio_preferences≈ 599 tokens

  Change / set / update the user's saved AUDIO (music) preferences — the defaults generate_track applies automatically to every new song (genre, vocal gender, language, instruments, default audio content type). Supplied fields replace their saved defaults without an undo history; omitted fields are preserved. Use this when the user wants to change their music style GOING FORWARD (e.g. "from now on make my songs jazz with female vocals", "always use Spanish for my songs"), NOT for a one-off — for a single song, pass the style to generate_track instead.

  Paramètres, retour & exemple (7)

  Paramètres

  • genre · string · optionnel
    Music genre, e.g. pop, rock, jazz, electronic, hiphop, rnb, country, classical.
  • language · string · optionnel
    Preferred song language as an ISO 639-1 code, e.g. 'en', 'fr', 'es'.
  • audioType · string · optionnel · song | meditation | instrumental
    Saved default audio preference. MCP generation currently supports song and atmosphere. Guided content is available only through its separate app workflow.
  • instruments · array · optionnel
    Preferred instruments.
  • vocalGender · string · optionnel · f | m
    Preferred vocal gender for generated songs: 'f' or 'm'.
  • additionalGenres · array · optionnel
    Additional canonical genres you enjoy, e.g. ["lofi_hiphop", "ambient"].
  • styleDescription · string · optionnel
    A rich free-text description of the music style you like, e.g. "warm intimate acoustic, like Bon Iver".

  Exemple d'appel

  {"name": "update_audio_preferences", "arguments": {"genre": "texte", "language": "texte", "audioType": "song", "instruments": [], "vocalGender": "f", "additionalGenres": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"updated": []}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.aiponge.com/mcp