ai.uwear/uwear

Est-ce que ai.uwear/uwear est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.uwear/uwear » 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 70 outils

• add_chat_photos_to_board≈ 1670 tokens

  Use this when the user attaches images in this chat and wants them in Uwear, on the Shoot Board or in a shoot: clothing, a Model, a Location or a reference. Put each attachment in its own field, image_file_1, image_file_2, ... in attachment order, as the chat provides it: ChatGPT passes the file itself, also when you see only a file name or path. Chat attachments only: a web address is refused (ask the user to attach that photo). kinds: {image_file_N: garment|avatar|location|reference} for photos whose kind the user said or is clear (avatar: a person to use as a Model); Uwear sorts the rest. Saves each photo to the library (a repeat is reused), adds it to the board and returns its pile and asset id for propose_brief / update_brief. A photo returned unsure lists two candidates: ask the user and call again with the same files and kinds.

  Paramètres, retour & exemple (13)

  Paramètres

  • kinds · object · optionnel
    What each photo is, when you can tell (garment: clothing; avatar: a person to use as a Model; location: a place; reference: a pose, mood or styling photo), or the user's answer for one that came back unsure: {image_file_N: kind}. A photo left out is sorted by Uwear.
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • image_file_1 · object · requis
    An image attached in this chat, passed as the chat provides it.
  • image_file_2 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_3 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_4 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_5 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_6 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_7 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_8 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_9 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • image_file_10 · object · optionnel
    An image attached in this chat, passed as the chat provides it.
  • upload_handles · object · optionnel
    Only the upload_handle values a previous call of this tool returned in upload_needed, after running their commands: {image_file_N: upload_handle}. Never the attachments themselves: those go in image_file_N.

  Exemple d'appel

  {"name": "add_chat_photos_to_board", "arguments": {"board_id": "texte", "image_file_1": {}}}

  Exemple de retour

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

• confirm_brief≈ 352 tokens

  Generate a Shoot Board brief: publishes its automation drafts, then starts one workflow run per look, charged per run. Spends credits: call it only after the user has seen the brief's looks and credit quote (get_brief) and agreed in chat. Pass the board's brief_revision (read_shoot_board) as expected_brief_revision and a fresh idempotency_key; the same idempotency_key never publishes, runs or charges twice. Follow the runs with mcp_brief_runs.

  Paramètres, retour & exemple (5)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • brief_id · integer · requis
  • idempotency_key · string · requis
    Retry key for one Generate tap: never runs or charges twice.
  • expected_total_credits · integer · optionnel
    The quote's total_credits the user saw.
  • expected_brief_revision · integer · requis
    The board's brief_revision shown with this brief.

  Exemple d'appel

  {"name": "confirm_brief", "arguments": {"board_id": "texte", "brief_id": 1, "idempotency_key": "texte", "expected_brief_revision": 1}}

  Exemple de retour

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

• create_location≈ 330 tokens

  Create a reusable location/scene reference from an image URL. If no description is supplied, the backend analyzes the image. Use the returned location_id in propose_brief/update_brief.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · requis
    Name for the reusable location/scene reference
  • tag_ids · array · optionnel
    Optional tag IDs to assign after creating the location
  • image_url · string · requis
    URL of the location/reference image
  • description · string · optionnel
    Optional location description. If omitted, the system analyzes the image.
  • thumbnail_url · string · optionnel
    Optional thumbnail URL
  • source_metadata · object · optionnel
    Optional provenance metadata for the source image

  Exemple d'appel

  {"name": "create_location", "arguments": {"name": "texte", "image_url": "texte"}}

  Exemple de retour

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

• create_tag≈ 168 tokens

  Create a new tag for organizing assets (garments, models, outfits, files, results, locations). Requires an active company workspace.

  Paramètres, retour & exemple (2)

  Paramètres

  • name · string · requis
    Tag name (unique within the company)
  • color · string · optionnel
    Optional hex color, e.g. '#22C55E'

  Exemple d'appel

  {"name": "create_tag", "arguments": {"name": "texte"}}

  Exemple de retour

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

• get_art_direction≈ 127 tokens

  Get a selectable ArtDirection by ID.

  Paramètres, retour & exemple (1)

  Paramètres

  • art_direction_id · integer · requis
    The ArtDirection ID to retrieve

  Exemple d'appel

  {"name": "get_art_direction", "arguments": {"art_direction_id": 1}}

  Exemple de retour

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

• get_brief≈ 153 tokens

  Read one of the account's Shoot Board briefs by brief_id: its looks, automations, credit quote and status. Changes nothing.

  Paramètres, retour & exemple (2)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • brief_id · integer · requis

  Exemple d'appel

  {"name": "get_brief", "arguments": {"board_id": "texte", "brief_id": 1}}

  Exemple de retour

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

• get_generation_results≈ 1090 tokens

  Look up generation results by exact IDs, filters, or hybrid image/name/SKU search. Returns labeled native ImageContent previews; use them directly and never Markdown-embed result URLs. They are display previews, not originals: url/download_url are originals, preview_url is the fallback link, and poster_url/thumbnail_url is a video poster. Every result includes generation_result_id and the response includes generation_result_ids; use those exact integers for queue_generation_result_qa/read_generation_result_qa or as durable generation_result command.source values in canonical edit, upscale, and video commands. Confirmation-gated clients use propose_brief(commands=[...], execute_immediately=true) when the user asked to run now, update_brief for a complete command replacement, or confirm_brief(execute=true) for a visible brief. Pass generation_result_id to fetch one result or generation_id to list a job's results. Defaults to compact result metadata. Set include_snapshot=true to recover full settings, resource snapshots and prior prompts. Use start_date/end_date for requests like 'last week'.

  Paramètres, retour & exemple (19)

  Paramètres

  • kind · string · optionnel
    Filter by type: 'Image', 'Edit', 'Upscale', 'Video'
  • page · integer · optionnel
    Page number for pagination
  • limit · integer · optionnel
    Number of items per page
  • query · string · optionnel
    Hybrid search across generated image content, originating item names, and SKUs.
  • tag_ids · array · optionnel
    Filter by tag IDs (results must have at least one)
  • decision · string · optionnel · approved | rejected | undecided
    Filter by the unified result verdict.
  • end_date · string · optionnel
    Filter results created on or before this ISO date/datetime, e.g. 2026-04-27.
  • model_ids · array · optionnel
    Filter results to images generated with these AI models
  • avatar_ids · array · optionnel
    Filter results to images generated with these avatars
  • outfit_ids · array · optionnel
    Filter results to images generated with these outfits
  • start_date · string · optionnel
    Filter results created on or after this ISO date/datetime, e.g. 2026-04-20.
  • qa_statuses · array · optionnel
    Filter by QA statuses, e.g. pending, processing, completed, error.
  • location_ids · array · optionnel
    Filter results to images generated with these locations
  • generation_id · integer · optionnel
    Filter by parent generation ID (lists all result images from one generation job)
  • decision_source · string · optionnel · auto | human
    Filter by the verdict source.
  • include_snapshot · boolean · optionnel
    Include full generation settings, resource snapshots and raw prompt payloads. Large; use only for prompt recovery.
  • art_direction_ids · array · optionnel
    Filter results to images generated with these art directions
  • clothing_item_ids · array · optionnel
    Filter results to images generated with these clothing items
  • generation_result_id · integer · optionnel
    Look up a single result image by its generation_result_id (the exact integer ID required by QA/edit/upscale/video tools). Returns that one result directly.

  Exemple d'appel

  {"name": "get_generation_results", "arguments": {"kind": "texte", "page": 1, "limit": 1, "query": "texte", "tag_ids": [], "decision": "approved"}}

  Exemple de retour

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

• get_generation_status≈ 412 tokens

  Check generation job status. Completed results may include labeled native ImageContent previews; use them directly and never Markdown-embed result URLs. They are display previews, not originals: url/download_url are originals, preview_url is the fallback link, and poster_url/thumbnail_url is a video poster. Returns compact status, parent/child generation IDs, camera, avatar_id, model_id, model_slug, use_case, net credits_charged, credits_refunded, estimated_processing_seconds, and status_guidance. Failed jobs also return a safe error_message and error_type (user, transient, or provider). Set include_snapshot=true to recover full settings, resource snapshots and prior prompts. Status can remain Created while queued/preparing; avoid tight polling loops. UI 'Gemini Pro' maps to model_slug nano-banana-pro or nano_banana_pro_clothing.

  Paramètres, retour & exemple (2)

  Paramètres

  • generation_id · integer · requis
    The generation ID to check. Returns compact status, avatar_id, model_id, model_slug, and use_case. UI 'Gemini Pro' maps to model_slug nano-banana-pro or nano_banana_pro_clothing.
  • include_snapshot · boolean · optionnel
    Include full generation settings, resource snapshots and raw prompt payloads. Large; use only for prompt recovery.

  Exemple d'appel

  {"name": "get_generation_status", "arguments": {"generation_id": 1}}

  Exemple de retour

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

• get_user_credits≈ 81 tokens

  Get user's current credit balance.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_user_credits", "arguments": {}}

  Exemple de retour

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

• list_art_directions≈ 300 tokens

  List selectable ArtDirections as compact summaries: visible system ArtDirections plus company ArtDirections. Use query to match exact names and natural-language creative requests. Use this as the catalog step before choosing an art_direction_id for a brief; if there is no clear match, fall back to the user's phrase as prompt/creative_context. Use get_art_direction for the full markdown document before reusing one in a brief.

  Paramètres, retour & exemple (3)

  Paramètres

  • page · integer · optionnel
    Page number for pagination
  • limit · integer · optionnel
    Number of compact ArtDirection summaries per page
  • query · string · optionnel
    Hybrid search across saved ArtDirection names and creative content.

  Exemple d'appel

  {"name": "list_art_directions", "arguments": {"page": 1, "limit": 1, "query": "texte"}}

  Exemple de retour

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

• list_avatars≈ 446 tokens

  List the user's Models: the reusable people who wear the Clothing (not the AI models; for those, use mcp_list_model_catalog). Supports structured filters or query for hybrid name/metadata/image-attribute search. Set include_image_url=true when the Model's image itself is needed.

  Paramètres, retour & exemple (9)

  Paramètres

  • page · integer · optionnel
    Page number for pagination
  • sort · string · optionnel
    Sort order: 'field:direction', e.g. 'created_at:desc'. Default: created_at:desc
  • limit · integer · optionnel
    Number of items per page
  • query · string · optionnel
    Hybrid search across avatar/model names, metadata, and visual attributes.
  • tag_ids · array · optionnel
    Filter to avatars with any of these tags
  • end_date · string · optionnel
    Filter: created on or before this date (ISO format)
  • avatar_ids · array · optionnel
    Filter to specific avatar IDs
  • start_date · string · optionnel
    Filter: created on or after this date (ISO format)
  • include_image_url · boolean · optionnel
    Set true when you need to inspect or reuse the avatar/model image URL.

  Exemple d'appel

  {"name": "list_avatars", "arguments": {"page": 1, "sort": "texte", "limit": 1, "query": "texte", "tag_ids": [], "end_date": "texte"}}

  Exemple de retour

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

• list_garments≈ 916 tokens

  List user's garments with structured filters or query for hybrid name/SKU/metadata/image-attribute search. body_zone expands to categories and is ORed with category when both are given. With a category or body_zone filter and include_uncategorized=false, uncategorized_count reports garments hidden by the category filter within the same scope. If matches are short and uncategorized_count > 0, call again with include_uncategorized=true and inspect those garments.

  Paramètres, retour & exemple (13)

  Paramètres

  • page · integer · optionnel
    Page number for pagination
  • sort · string · optionnel
    Sort order: 'field:direction', e.g. 'created_at:desc', 'clothing_item_name:asc'. Default: created_at:desc
  • limit · integer · optionnel
    Number of items per page
  • query · string · optionnel
    Hybrid search across garment names, SKUs, metadata, and visual attributes.
  • tag_ids · array · optionnel
    Filter to garments with any of these tags
  • category · array · optionnel
    Filter to garments in any of these canonical categories; OR with body_zone when both are given.
  • end_date · string · optionnel
    Filter: created on or before this date (ISO format)
  • body_zone · array · optionnel
    Filter to categories in any of these body zones; OR with category when both are given.
  • start_date · string · optionnel
    Filter: created on or after this date (ISO format, e.g. '2025-06-01')
  • clothing_item_ids · array · optionnel
    Filter to specific garment IDs
  • include_image_url · boolean · optionnel
    Set true when the garment image itself is needed for visual display or reuse.
  • include_uncategorized · boolean · optionnel
    Also include garments with no category when category and/or body_zone filters are used. If the first result has uncategorized_count > 0 and too few matches, call again with true and inspect those garments.
  • exclude_clothing_item_ids · array · optionnel
    Exclude these garment IDs, for example the attached garment.

  Exemple d'appel

  {"name": "list_garments", "arguments": {"page": 1, "sort": "texte", "limit": 1, "query": "texte", "tag_ids": [], "category": []}}

  Exemple de retour

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

• list_locations≈ 444 tokens

  List reusable location/scene reference images by structured filters or query: IDs, tags, date range, and sort. Use when the user wants to pick a saved background/location reference for a generation.

  Paramètres, retour & exemple (9)

  Paramètres

  • page · integer · optionnel
    Page number for pagination
  • sort · string · optionnel
    Sort order: 'field:direction', e.g. 'created_at:desc', 'location_name:asc'. Default: created_at:desc
  • limit · integer · optionnel
    Number of items per page
  • query · string · optionnel
    Hybrid search across location names, metadata, and visual attributes.
  • tag_ids · array · optionnel
    Filter to locations with any of these tags
  • end_date · string · optionnel
    Filter: created on or before this date (ISO format)
  • start_date · string · optionnel
    Filter: created on or after this date (ISO format)
  • location_ids · array · optionnel
    Filter to specific location IDs
  • include_image_url · boolean · optionnel
    Set true when the location/reference image URL is needed for inspection or reuse.

  Exemple d'appel

  {"name": "list_locations", "arguments": {"page": 1, "sort": "texte", "limit": 1, "query": "texte", "tag_ids": [], "end_date": "texte"}}

  Exemple de retour

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

• list_outfits≈ 480 tokens

  List user's outfits (saved garment combinations). Filter by garment IDs, active status, date range, or query against contained garments.

  Paramètres, retour & exemple (11)

  Paramètres

  • page · integer · optionnel
    Page number for pagination
  • sort · string · optionnel
    Sort: 'field:direction'. Use 'latest_generation_at:desc' to surface recently generated outfits. Default: created_at:desc
  • limit · integer · optionnel
    Number of items per page
  • query · string · optionnel
    Search outfit names and contained garments.
  • source · string · optionnel · manual | auto | proposed
    Filter by outfit source.
  • tag_ids · array · optionnel
    Filter to outfits with any of these tags
  • end_date · string · optionnel
    Filter: created on or before this date (ISO format)
  • is_active · string · optionnel
    Filter by status: 'true', 'false', or 'both' (default: both)
  • outfit_ids · array · optionnel
    Filter to specific outfit IDs
  • start_date · string · optionnel
    Filter: created on or after this date (ISO format)
  • clothing_item_ids · array · optionnel
    Filter to outfits containing any of these garments

  Exemple d'appel

  {"name": "list_outfits", "arguments": {"page": 1, "sort": "texte", "limit": 1, "query": "texte", "source": "manual", "tag_ids": []}}

  Exemple de retour

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

• list_tags≈ 158 tokens

  List available tags for the user's company. Use this to resolve user-provided tag names like 'summer26' before selecting garments, outfits, models, files, generations, or locations. For no-UI MCP flows, find the tag ID here, then call get_items_by_tag or the relevant list_* tool with tag_ids.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_tags", "arguments": {}}

  Exemple de retour

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

• list_templates≈ 457 tokens

  List canonical company templates, optionally filtered by kind, scope, command use case, or public t-xxxx share code. Templates persist canonical commands but do not execute generations. System templates named `Demo — …` are worked examples of the canonical command language; read one with `get_template` before authoring a first brief or workflow.

  Paramètres, retour & exemple (6)

  Paramètres

  • page · integer · optionnel
    Page number for pagination
  • use_case · string · optionnel
    Filter by a use_case present in any stored command
  • share_code · string · optionnel
    Return the template assigned this public t-xxxx share code
  • catalog_scope · ? · optionnel
    Filter by library or owner_only. Owner-only templates are hidden unless explicitly requested.
  • template_kind · ? · optionnel
    Filter generation presets or read-only historical batch_workflow records
  • items_per_page · integer · optionnel
    Number of templates per page

  Exemple d'appel

  {"name": "list_templates", "arguments": {"page": 1, "use_case": "texte", "share_code": "texte", "catalog_scope": "texte", "template_kind": "texte", "items_per_page": 1}}

  Exemple de retour

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

• mcp_add_context≈ 563 tokens

  Append items to the Uwear Shoot Board.

  Paramètres, retour & exemple (4)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • board_version · integer · optionnel · 2
    Pass 2 to receive board v2 state, including the board's output settings
  • context_items · array · requis
    Shoot Board items to append to the current list
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "mcp_add_context", "arguments": {"board_id": "texte", "context_items": [], "expected_revision": 1}}

  Exemple de retour

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

• mcp_add_garment_view≈ 410 tokens

  A Clothing card dropped on another. The photo of from_garment_id becomes the back, side or detail view of garment_id, and from_garment_id leaves the board (deleted only when it is a fresh drop nothing else uses). Or a photo put in the brief's missing-photo slot: image_url instead of from_garment_id, nothing leaves the board. The board's draft brief is saved again when the view changes it. Returns the board (and brief); asking again answers status unchanged.

  Paramètres, retour & exemple (6)

  Paramètres

  • view · string · requis · back | side | detail
    back, side, or detail (a close-up)
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • image_url · string · optionnel
    instead of from_garment_id: the stored photo (host file download URL, or the image_url mcp_upload_intake_photo returned)
  • garment_id · integer · requis
    the board garment that gains the photo as a view
  • from_garment_id · integer · optionnel
    the board garment whose photo it is; it leaves the board
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "mcp_add_garment_view", "arguments": {"view": "back", "board_id": "texte", "garment_id": 1, "expected_revision": 1}}

  Exemple de retour

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

• mcp_brief_list≈ 160 tokens

  The account's Shoot Board briefs, newest first: every brief that ran (on any Shoot Board) and this board's draft, each with its status, looks, automations, credits and covers.

  Paramètres, retour & exemple (2)

  Paramètres

  • page · integer · optionnel
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "mcp_brief_list", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_brief_runs≈ 234 tokens

  Every look's run of a generating brief (brief_id), or runs by id (workflow_run_ids, each with the look its cards held): status, results by step, credits.

  Paramètres, retour & exemple (3)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • brief_id · integer · optionnel
  • workflow_run_ids · array · optionnel

  Exemple d'appel

  {"name": "mcp_brief_runs", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_clear_context≈ 272 tokens

  Clear all Shoot Board items, or only one context type.

  Paramètres, retour & exemple (4)

  Paramètres

  • type · string · optionnel · clothing | models | outfits | generations | file | files | location | locations
    Context type to remove; omit to clear the entire Shoot Board
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • board_version · integer · optionnel · 2
    Pass 2 to receive board v2 state, including the board's output settings
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "mcp_clear_context", "arguments": {"board_id": "texte", "expected_revision": 1}}

  Exemple de retour

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

• mcp_commit_intake≈ 408 tokens

  Save sorted Shoot Board photos to the library as garments, avatars, locations or reference files, skip ones already saved, and add them to the Shoot Board at expected_revision; a board that changed is refused before anything is saved (revision_conflict with the current board).

  Paramètres, retour & exemple (3)

  Paramètres

  • items · array · requis
    Photos to save, each with its confirmed kind
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "mcp_commit_intake", "arguments": {"items": [], "board_id": "texte", "expected_revision": 1}}

  Exemple de retour

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

• mcp_delete_generation_results≈ 158 tokens

  Delete the user's results and their stored images, as the platform's Delete. Cannot be undone: call it only after the user confirmed in chat which results to delete.

  Paramètres, retour & exemple (1)

  Paramètres

  • generation_result_ids · array · requis

  Exemple d'appel

  {"name": "mcp_delete_generation_results", "arguments": {"generation_result_ids": []}}

  Exemple de retour

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

• mcp_edit_brief≈ 1637 tokens

  Edit the Shoot Board's brief by hand: add, remove or change looks, or run looks through another automation. Saves a new brief linked to the board and returns the board, the brief, its quote and the credit delta; dry_run only quotes.

  Paramètres, retour & exemple (5)

  Paramètres

  • ops · array · requis
  • dry_run · boolean · optionnel
    Quote the edit and its credit delta; save nothing.
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • brief_id · integer · requis
    The board's brief (board.brief_id).
  • expected_brief_revision · integer · requis
    The board's brief_revision shown with the brief.

  Exemple d'appel

  {"name": "mcp_edit_brief", "arguments": {"ops": [], "board_id": "texte", "brief_id": 1, "expected_brief_revision": 1}}

  Exemple de retour

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

• mcp_export_montage≈ 332 tokens

  Export montage clips as one stitched video. Spends credits: call it only after the user confirmed the clips and their order in chat. Returns the generation_id to poll with get_generation_status.

  Paramètres, retour & exemple (4)

  Paramètres

  • clips · array · requis
    Ordered generation-result clips to stitch into the montage
  • fit_mode · string · requis
    How each clip fits the output frame: contain or cover
  • aspect_ratio · string · requis
    Output video aspect ratio in W:H format
  • base_resolution · integer · requis
    Output base resolution in pixels

  Exemple d'appel

  {"name": "mcp_export_montage", "arguments": {"clips": [], "fit_mode": "texte", "aspect_ratio": "texte", "base_resolution": 1}}

  Exemple de retour

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

• mcp_extract_video_frame≈ 162 tokens

  Save a still frame of a video result as a new image result, as POST /generation-result/{id}/extract-frame. The result viewer's Save frame.

  Paramètres, retour & exemple (2)

  Paramètres

  • timestamp_seconds · number|null · optionnel
    Frame time in seconds; omit for the last frame.
  • generation_result_id · integer · requis

  Exemple d'appel

  {"name": "mcp_extract_video_frame", "arguments": {"generation_result_id": 1}}

  Exemple de retour

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

• mcp_generate_clip≈ 415 tokens

  Queue an image-to-video generation for one montage clip. Spends credits: call it only after the user agreed in chat. Returns the generation_id to poll with get_generation_status.

  Paramètres, retour & exemple (9)

  Paramètres

  • model · string · requis
    Video model slug or supported model name
  • prompt · string|null · optionnel
    Optional motion prompt for the video clip
  • duration · integer|null · optionnel
    Video duration in seconds; defaults to 5
  • image_url · string|null · optionnel
    HTTPS source image URL; provide exactly one source
  • resolution · string|null · optionnel
    Optional output resolution; defaults to 480p
  • generate_audio · boolean|null · optionnel
    Include audio in the delivered video. False delivers a silent file; fixed-audio providers are muted after generation at the same credits.
  • last_frame_url · string|null · optionnel
    Optional final-frame image URL for supported video models
  • uploaded_file_id · integer|null · optionnel
    Uploaded file ID to use as the source image; provide exactly one source
  • generation_result_id · integer|null · optionnel
    Existing generation result ID to use as the source image; provide exactly one source

  Exemple d'appel

  {"name": "mcp_generate_clip", "arguments": {"model": "texte"}}

  Exemple de retour

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

• mcp_get_context≈ 138 tokens

  Read the Uwear Shoot Board.

  Paramètres, retour & exemple (2)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • board_version · integer · optionnel · 2
    Pass 2 to receive board v2 state, including the board's output settings

  Exemple d'appel

  {"name": "mcp_get_context", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_intake_files≈ 319 tokens

  Sort photos dropped on the Shoot Board into garment, avatar, location or reference (or unsure with two candidates) and report duplicates within the drop and in the library. Saves nothing. A photo the call had no time left for comes back with error deferred: send it again.

  Paramètres, retour & exemple (2)

  Paramètres

  • files · array · requis
    Dropped photos, in drop order; results use the same index
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "mcp_intake_files", "arguments": {"files": []}}

  Exemple de retour

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

• mcp_list_files≈ 205 tokens

  List uploaded (reference) files for the Uwear MCP workspace files tab and the Shoot Board's References tab.

  Paramètres, retour & exemple (4)

  Paramètres

  • page · integer · optionnel
    Page number for uploaded file results
  • limit · integer · optionnel
    Maximum number of uploaded files per page
  • query · string · optionnel
    Optional search over file names and tags (the Shoot Board's References tab)
  • tag_ids · array · optionnel
    Optional: only files with any of these tags

  Exemple d'appel

  {"name": "mcp_list_files", "arguments": {"page": 1, "limit": 1, "query": "texte", "tag_ids": []}}

  Exemple de retour

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

• mcp_list_model_catalog≈ 101 tokens

  The active AI models with their capabilities and pricing rules, as GET /models returns them, for the widget's model pickers.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "mcp_list_model_catalog", "arguments": {}}

  Exemple de retour

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

• mcp_read_generation≈ 123 tokens

  One generation with its results as GET /generation/{id} returns it (prompt, model, settings, inputs), for the result viewer's Info panel.

  Paramètres, retour & exemple (1)

  Paramètres

  • generation_id · integer · requis

  Exemple d'appel

  {"name": "mcp_read_generation", "arguments": {"generation_id": 1}}

  Exemple de retour

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

• mcp_read_generation_result≈ 128 tokens

  One generation result as GET /generation-result/{id} returns it (tags, review verdict, QA, prompt, model), for the widget's result viewer.

  Paramètres, retour & exemple (1)

  Paramètres

  • generation_result_id · integer · requis

  Exemple d'appel

  {"name": "mcp_read_generation_result", "arguments": {"generation_result_id": 1}}

  Exemple de retour

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

• mcp_recipe_copy≈ 216 tokens

  Copy an automation as a new automation for this shoot.

  Paramètres, retour & exemple (4)

  Paramètres

  • name · string · optionnel
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • source_version_id · string · optionnel
  • source_workflow_id · string · requis

  Exemple d'appel

  {"name": "mcp_recipe_copy", "arguments": {"board_id": "texte", "source_workflow_id": "texte"}}

  Exemple de retour

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

• mcp_recipe_history≈ 195 tokens

  An automation's past runs, newest first: one row per Shoot Board Generate (its looks) or per run started on Uwear, with when, how it went, credits and covers.

  Paramètres, retour & exemple (3)

  Paramètres

  • page · integer · optionnel
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • workflow_id · string · requis

  Exemple d'appel

  {"name": "mcp_recipe_history", "arguments": {"board_id": "texte", "workflow_id": "texte"}}

  Exemple de retour

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

• mcp_recipe_list≈ 254 tokens

  The company's shoot automations (and other automations to copy).

  Paramètres, retour & exemple (6)

  Paramètres

  • page · integer · optionnel
  • query · string · optionnel
    Name search.
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • items_per_page · integer · optionnel
  • include_automations · boolean · optionnel
    Also list automations (read/copy only).
  • include_definitions · boolean · optionnel
    Also return each listed automation's live graph (the cards that draw its steps).

  Exemple d'appel

  {"name": "mcp_recipe_list", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_recipe_open≈ 314 tokens

  Open the brief's automation in the builder: its draft, or once Generate published it its live version (saving an edit of it makes a new automation); another automation opens read-only.

  Paramètres, retour & exemple (4)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • read_only · boolean · optionnel
    Show a published version (version_id, else the live one) without opening a draft: a brief that ran shows what it ran, the board's pinned Automation its live version.
  • version_id · string · optionnel
    The published version to show (an automation, or read_only); a brief recipe opened to edit always opens its draft.
  • workflow_id · string · requis

  Exemple d'appel

  {"name": "mcp_recipe_open", "arguments": {"board_id": "texte", "workflow_id": "texte"}}

  Exemple de retour

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

• mcp_recipe_preflight≈ 223 tokens

  Validate and price the automation being edited.

  Paramètres, retour & exemple (4)

  Paramètres

  • graph · object · requis
    The unsaved authoring graph (as the builder holds it).
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • version_id · string · requis
  • workflow_id · string · requis

  Exemple d'appel

  {"name": "mcp_recipe_preflight", "arguments": {"graph": {}, "board_id": "texte", "version_id": "texte", "workflow_id": "texte"}}

  Exemple de retour

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

• mcp_recipe_save_draft≈ 366 tokens

  Save the automation's draft.

  Paramètres, retour & exemple (10)

  Paramètres

  • edges · array · requis
  • nodes · array · requis
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • version_id · string · optionnel
  • workflow_id · string · requis
  • failure_policy · string · optionnel
  • base_version_id · string · optionnel
  • contract_version · string · optionnel
  • result_projection · array · optionnel
  • expected_definition_hash · string · optionnel

  Exemple d'appel

  {"name": "mcp_recipe_save_draft", "arguments": {"edges": [], "nodes": [], "board_id": "texte", "workflow_id": "texte"}}

  Exemple de retour

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

• mcp_reclassify_board_item≈ 340 tokens

  Move a Shoot Board photo between the Clothing, Models and Locations piles. Saves the same image as the new kind and swaps it on the board; the old asset is deleted only if intake saved it in the last 24 hours and nothing uses it, otherwise it stays in the library. Asking for a move that already happened changes nothing and returns the board (status "unchanged").

  Paramètres, retour & exemple (4)

  Paramètres

  • to · string · requis · clothing | models | locations
    The pile to move it to
  • item · object · requis
    The board item to move
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "mcp_reclassify_board_item", "arguments": {"to": "clothing", "item": {}, "board_id": "texte", "expected_revision": 1}}

  Exemple de retour

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

• mcp_replace_context≈ 1103 tokens

  Replace the Uwear Shoot Board items.

  Paramètres, retour & exemple (5)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • board_version · integer · optionnel · 2
    Pass 2 to receive board v2 state, including the board's output settings
  • context_items · array · optionnel
    Shoot Board items that replace the current list when context_state is omitted
  • context_state · object · optionnel
    Complete Shoot Board state to sanitize and persist; takes precedence over context_items
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "mcp_replace_context", "arguments": {"board_id": "texte", "expected_revision": 1}}

  Exemple de retour

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

• mcp_review_generation_results≈ 198 tokens

  The result viewer's review rail. Sets the user's verdict on their own results to approved or rejected, or clears it (decision null), replacing any verdict they had; deletes nothing and spends no credits.

  Paramètres, retour & exemple (3)

  Paramètres

  • note · string|null · optionnel
  • decision · string|null · requis · approved | rejected | None
  • generation_result_ids · array · requis

  Exemple d'appel

  {"name": "mcp_review_generation_results", "arguments": {"decision": "approved", "generation_result_ids": []}}

  Exemple de retour

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

• mcp_save_retouch≈ 260 tokens

  Save an edited image (image_base64) as a new child result of parent_generation_result_id. Changes no existing result.

  Paramètres, retour & exemple (5)

  Paramètres

  • file_name · string|null · optionnel
    Optional filename for the saved retouched image
  • mime_type · string|null · optionnel
    Optional image MIME type; inferred from a data URL or defaults to image/png
  • operations · ? · optionnel
    Optional retouch operation metadata stored with the child result
  • image_base64 · string · requis
    Retouched image encoded as base64 or an image data URL
  • parent_generation_result_id · integer · requis
    Generation result ID of the original image

  Exemple d'appel

  {"name": "mcp_save_retouch", "arguments": {"image_base64": "texte", "parent_generation_result_id": 1}}

  Exemple de retour

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

• mcp_set_generation_result_tags≈ 172 tokens

  Replace a result's tags with tag_ids (empty removes all), as PUT /generation-result/{id}/tags. The result viewer's tag tray. A tag that starts one of the user's automations starts it, as on the platform.

  Paramètres, retour & exemple (2)

  Paramètres

  • tag_ids · array · requis
  • generation_result_id · integer · requis

  Exemple d'appel

  {"name": "mcp_set_generation_result_tags", "arguments": {"tag_ids": [], "generation_result_id": 1}}

  Exemple de retour

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

• mcp_update_tag≈ 138 tokens

  Rename or recolor one of the company's tags, as PATCH /tag/{id}. The result viewer's tag tray.

  Paramètres, retour & exemple (3)

  Paramètres

  • name · string|null · optionnel
  • color · string|null · optionnel
  • tag_id · integer · requis

  Exemple d'appel

  {"name": "mcp_update_tag", "arguments": {"tag_id": 1}}

  Exemple de retour

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

• mcp_upload_intake_photo≈ 330 tokens

  Store one photo dropped on the Shoot Board, sent inline as base64, for a host that cannot upload files itself. Returns a receipt (sha256, size, stored, image_url, image_url_expires_at); pass image_url to mcp_intake_files and mcp_commit_intake. Without data, stores nothing and returns the receipt of the photo already stored under sha256 (a fresh image_url), or stored: false.

  Paramètres, retour & exemple (3)

  Paramètres

  • data · string · optionnel
    The image bytes, standard base64, at most 4 MiB decoded (downscale larger photos). Omit it to ask for the receipt of a photo already stored
  • sha256 · string · requis
    Hex SHA-256 of the dropped file as the user picked it (the intake tools take the same value), even when data is a downscaled copy
  • content_type · string · optionnel · image/jpeg | image/png | image/webp | image/avif | image/gif | image/bmp | image/tiff
    Image MIME type of data (required with data)

  Exemple d'appel

  {"name": "mcp_upload_intake_photo", "arguments": {"sha256": "texte"}}

  Exemple de retour

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

• mcp_workflow_assets≈ 168 tokens

  The automation builder reads library items (Clothing, Models, Locations, ...) of one kind by id to show them on its cards. Read-only.

  Paramètres, retour & exemple (3)

  Paramètres

  • ids · array · requis
  • kind · string · requis
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "mcp_workflow_assets", "arguments": {"ids": [], "kind": "texte", "board_id": "texte"}}

  Exemple de retour

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

• mcp_workflow_cameras≈ 132 tokens

  The camera views (front, side, back, crops) a shot or camera edit can use, for the automation builder. Read-only.

  Paramètres, retour & exemple (1)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "mcp_workflow_cameras", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_workflow_contract≈ 146 tokens

  The automation format (step kinds and their settings) the automation builder edits against. Read-only.

  Paramètres, retour & exemple (2)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • contract_version · string · optionnel

  Exemple d'appel

  {"name": "mcp_workflow_contract", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_workflow_gallery≈ 238 tokens

  The automation builder's picker: one page of the user's library items of one kind, filtered by search text, tags or category. Read-only.

  Paramètres, retour & exemple (7)

  Paramètres

  • kind · string · requis
  • page · integer · optionnel
  • query · string · optionnel
  • tag_ids · array · optionnel
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • page_size · integer · optionnel
  • categories · array · optionnel

  Exemple d'appel

  {"name": "mcp_workflow_gallery", "arguments": {"kind": "texte", "board_id": "texte"}}

  Exemple de retour

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

• mcp_workflow_garment_categories≈ 129 tokens

  The garment categories, for the automation builder's category filters. Read-only.

  Paramètres, retour & exemple (1)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "mcp_workflow_garment_categories", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• mcp_workflow_tags≈ 122 tokens

  The account's tags, for the automation builder's tag filters. Read-only.

  Paramètres, retour & exemple (1)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "mcp_workflow_tags", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• modify_shoot_board≈ 771 tokens

  Use this when the user asks in chat to change what is on the open Shoot Board. add puts items on it; set replaces the whole item list (to remove items, send the ones to keep); clear empties one type, or without type starts a new shoot on the same board (its brief is unlinked; photos stay in the library); add_as_view makes from_garment_id's photo the back, side or detail view of garment_id and takes from_garment_id off the board, only after the user agrees the two show one garment. Items are {type, id} from search_uwear_library or read_shoot_board. To reuse an automation, add {type: automations, id: a workflow_id from brief_inputs.automations}: the board pins one and the next brief runs every look through it. Pass expected_revision from read_shoot_board; on revision_conflict, apply the change to the returned board once.

  Paramètres, retour & exemple (8)

  Paramètres

  • type · string · optionnel · clothing | models | outfits | generations | files | locations | art_directions | automations
    clear: only this type; omit for a new shoot (the whole board and its brief)
  • view · string · optionnel · back | side | detail
    add_as_view: back, side, or detail (a close-up)
  • items · array · optionnel
    add / set: the items. An automations item (id: a workflow_id from brief_inputs.automations) pins the Automation every look of the brief runs through; a board pins one, a new one replaces it. A board holds one art direction the same way
  • action · string · requis · add | set | clear | add_as_view
    add: put items on the board; set: replace all items; clear: remove one type, or without type everything and the board's brief (a new shoot on this board); add_as_view: from_garment_id's photo becomes a view of garment_id
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • garment_id · integer · optionnel
    add_as_view: the board garment that gains the photo as a view
  • from_garment_id · integer · optionnel
    add_as_view: the board garment whose photo it is; it leaves the board
  • expected_revision · integer · requis
    Board revision this write is based on; a stale revision returns a revision_conflict error with the current board instead of overwriting it

  Exemple d'appel

  {"name": "modify_shoot_board", "arguments": {"action": "add", "board_id": "texte", "expected_revision": 1}}

  Exemple de retour

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

• propose_brief≈ 1672 tokens

  Use this when the user describes a shoot. Saves a brief, the looks to shoot and the automation they run through, and links it to the board in place of the current one. Nothing runs or is charged: show the user the looks and the credit quote (get_brief), and generate with confirm_brief only after they agree. Read the board first with read_shoot_board and follow brief_inputs.guide. If the result lists problems, fix them all and call again.

  Paramètres, retour & exemple (6)

  Paramètres

  • looks · array · requis
    The looks to shoot, each one outfit worn in the shoot, with ids from read_shoot_board.
  • title · string · optionnel
    The shoot's name, only in the user's own words; otherwise leave it out.
  • recipe · ? · optionnel
    The shots and steps the user described (views, crops, edits, upscale, video): Uwear builds them as a new automation. Not with recipe_workflow_id.
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • direction · ? · requis
    Required: what every shot of every look follows, exactly what Generate runs: prompt, art_direction_id (a saved art direction), or both. Write one direction for every look from what the user wants (setting, light, mood, poses, purpose). Never name a garment, model, location or look: the same words run on every look.
  • recipe_workflow_id · string · optionnel
    An automation from read_shoot_board's brief_inputs.automations that every look runs through as is (only when it matches what the user asked for). Not with recipe. Omitted while the board pins one (brief_inputs.pinned_automation): every look runs it.

  Exemple d'appel

  {"name": "propose_brief", "arguments": {"looks": [], "board_id": "texte", "direction": "texte"}}

  Exemple de retour

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

• propose_montage≈ 1230 tokens

  ONLY for video montage/stitching/export workflows. Use when the user explicitly asks to create a montage, stitch clips, make a reel, export a video sequence, make video clips from images, or combine images/videos into one final video. Never use this for a photoshoot, lookbook, product shoot, collection shoot, outfit shoot, garment shoot, or image-generation request; those must use request_user_context followed by propose_brief/update_brief. Do not call this merely because selected context contains images, generations, garments, or models. A photoshoot may later feed a montage, but the photoshoot itself must be proposed as a BriefProposal first. PROPOSES the montage for user review — user can edit clips, generate missing videos, then export. Supports: existing videos with optional trim (`target_duration` or `start_time`/`end_time`), images that need video generation (specify video_model + a bespoke per-image motion prompt, and optionally `target_duration` or `duration`), per-clip speed/mute, global aspect ratio. If the user asks for clips to be e.g. '3 seconds each', set `target_duration: 3` on every item, including image items. For image items, avoid generic repeated prompts: tailor each prompt to the specific image and any requested zoom, movement, energy, or camera direction. If motion is not specified, inspect the image first with view_image and then write a fitting motion prompt from the image content before proposing. The user reviews and confirms in the UI. Export is free (0 credits); video generation clips cost credits per their model.

  Paramètres, retour & exemple (4)

  Paramètres

  • items · array · requis
    Ordered list of montage items. Each is either an existing video or an image needing video generation. Min 1, max 10.
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • aspect_ratio · string · optionnel
    Output aspect ratio (e.g. '9:16', '16:9', '1:1')
  • base_resolution · integer · optionnel
    Output resolution height in pixels

  Exemple d'appel

  {"name": "propose_montage", "arguments": {"items": []}}

  Exemple de retour

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

• queue_generation_result_qa≈ 407 tokens

  Default tool for generation-result QA. Use this whenever the user asks to QA, quality check, validate, review, inspect for defects, approve/reject, or assess already-created generation results. Do not substitute view_image for QA unless the user explicitly asks for a manual visual critique instead of the official Uwear QA pipeline. First identify the numeric generation_result_ids, then call this tool, then call read_generation_result_qa for the same IDs. Queued or requeued QA costs 1 credit per generation result; already-completed QA rows are not charged again. QA is built for scale — validating large batches (hundreds or thousands of results). When the user is iterating on a handful of results one by one, do not queue QA on your own initiative; run it when the user asks for it or when operating at batch scale.

  Paramètres, retour & exemple (2)

  Paramètres

  • max_qa_retries · integer · optionnel
    Maximum QA-triggered retry generations to allow. Retry generations can cost additional generation credits.
  • generation_result_ids · array · requis
    Generation result IDs to QA. Queued or requeued QA costs 1 credit per result.

  Exemple d'appel

  {"name": "queue_generation_result_qa", "arguments": {"generation_result_ids": []}}

  Exemple de retour

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

• read_generation_result_qa≈ 208 tokens

  Read official Uwear QA status, decision, and structured QA JSON for existing generation results. Call this after queue_generation_result_qa when the user asks to QA/check/validate/review generated outputs; summarize the structured decision and issues, not a manual view_image opinion.

  Paramètres, retour & exemple (1)

  Paramètres

  • generation_result_ids · array · requis
    Generation result IDs to read QA for

  Exemple d'appel

  {"name": "read_generation_result_qa", "arguments": {"generation_result_ids": []}}

  Exemple de retour

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

• read_shoot_board≈ 212 tokens

  Use this before modify_shoot_board, propose_brief or update_brief: the user changes the board in the widget at any time. Returns the board's items (Clothing, Models, Outfits, Locations, art directions, files, results) with ids and names, its revision, its linked brief_id, and brief_inputs: the guide, asset facts, automations, cameras, AI models and limits a brief is written from. Changes nothing.

  Paramètres, retour & exemple (1)

  Paramètres

  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.

  Exemple d'appel

  {"name": "read_shoot_board", "arguments": {"board_id": "texte"}}

  Exemple de retour

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

• request_user_context≈ 366 tokens

  Use this when the user wants a photoshoot and you have no board_id yet. Creates a new, empty Uwear Shoot Board and returns its board_id, which every other Shoot Board tool takes. This client shows no widget: build the shoot with tools (search_uwear_library, modify_shoot_board, propose_brief) and tell the user what is on the board. prompt: one line describing the shoot; expected_types: what it needs.

  Paramètres, retour & exemple (4)

  Paramètres

  • prompt · string · requis
    Instruction shown to the user, e.g. 'Select the clothing items you want to use and add them to the Shoot Board'
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • min_items · integer · optionnel
    Minimum number of items the user must provide
  • expected_types · array · requis
    Accepted item types (match panel tabs): 'clothing', 'models', 'outfits', 'generations', 'files'. Legacy 'file' is accepted as an alias for 'files'.

  Exemple d'appel

  {"name": "request_user_context", "arguments": {"prompt": "texte", "expected_types": []}}

  Exemple de retour

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

• save_art_direction≈ 818 tokens

  Use this when the user asks to create, write or save an art direction, or the board's New art direction asks for one: write it from their words, the chat and the board, and save it in the same turn. Saves it to the library and makes it the board's one art direction, replacing the previous one (which stays in the library). Fill every section with concrete, photographable choices. It applies to every look, so it names no garment, outfit, Model or Location (text naming a board item is refused). If the board has a brief, apply it with update_brief art_direction_id. If the result lists problems, fix them all and call again.

  Paramètres, retour & exemple (12)

  Paramètres

  • mood · string · requis
    The feeling and the pose language: energy, expression, how the model moves.
  • name · string · requis
    Its title, 2-6 words, the one you used in chat (never Untitled or Art direction).
  • avoid · array · optionnel
    What never appears, one per line.
  • light · string · requis
    Direction, softness, colour temperature and shadows (e.g. low warm sun from the left, long soft shadows).
  • camera · string · requis
    Framing, angle, lens feel and distance (e.g. eye-level 50mm, full body with headroom).
  • palette · string · requis
    The colours of set, light and styling (e.g. terracotta, sand, washed olive).
  • setting · string · requis
    Where it is shot: studio backdrop or place, surfaces, props.
  • styling · string · requis
    How the clothes are worn, hair, makeup, accessories, footwear.
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • overview · string · requis
    What the photos should feel like overall, in 1-2 sentences.
  • must_keep · array · optionnel
    Rules every photo keeps, one per line (the user's own must-haves).
  • variations · array · optionnel
    Only when the user wants variety across photos: each a name (Pose, Backdrop) and 2-6 complete alternatives Uwear rotates through.

  Exemple d'appel

  {"name": "save_art_direction", "arguments": {"mood": "texte", "name": "texte", "light": "texte", "camera": "texte", "palette": "texte", "setting": "texte"}}

  Exemple de retour

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

• save_reference_file_from_chat_file≈ 1588 tokens

  Batch save reference images from chat attachments into the Files library. Keep file metadata in files[] and pass top-level image_file_1, image_file_2, etc. in the same order. No base64, no local paths. Use for mood boards, backgrounds, and other reference images that are not Clothing or Models.

  Paramètres, retour & exemple (15)

  Paramètres

  • files · array · optionnel
    Reference file metadata in the same order as image_file_1, image_file_2, etc. No base64.
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • file_name · string · optionnel
    Single recovered display name
  • image_url · string · optionnel
    Single resolved download URL used by automatic opaque-file recovery.
  • mime_type · string · optionnel
    Single recovered MIME/content type, e.g. image/png
  • image_file_1 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_2 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_3 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_4 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_5 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_6 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_7 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_8 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_9 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_10 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.

  Exemple d'appel

  {"name": "save_reference_file_from_chat_file", "arguments": {"files": [], "board_id": "texte", "file_name": "texte", "image_url": "texte", "mime_type": "texte", "image_file_1": {}}}

  Exemple de retour

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

• search_uwear_library≈ 484 tokens

  Use this when the user names Clothing, Models, Locations, art directions, files or past results in chat and you need their ids. Takes a short keyword query (2-5 words, or an exact name, SKU or id) and returns typed ids, names and thumbnails. It finds items; it does not recommend them. Changes nothing.

  Paramètres, retour & exemple (5)

  Paramètres

  • limit · integer · optionnel
    Maximum number of hybrid matches to return
  • query · string · requis
    Short keyword query: 2 to 5 words, one concept per call, or an exact name/SKU/ID. Every word must match for lexical results, so long sentences can return no lexical matches. Describing a garment finds that garment, not pieces to pair with it.
  • item_types · array · optionnel
    Optional item types to search. Omit to search clothing, avatars/models, locations, art directions, uploaded files, and generation results.
  • refresh_index · boolean · optionnel
    Deprecated compatibility input. No index refresh is performed, even when true. Search uses the maintained index and current lexical metadata. Leave false.
  • exclude_clothing_item_ids · array · optionnel
    Exclude these garment IDs after ranking and before the result limit; other item types are unaffected.

  Exemple d'appel

  {"name": "search_uwear_library", "arguments": {"query": "texte"}}

  Exemple de retour

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

• set_generation_result_favorite≈ 191 tokens

  The result viewer's star. Marks one of the user's own generation results as a favorite (favorite true) or removes the mark (false); deletes nothing and spends no credits.

  Paramètres, retour & exemple (2)

  Paramètres

  • is_favorite · boolean · requis
    True to favorite, false to unfavorite
  • generation_result_id · integer · requis
    The generation result ID

  Exemple d'appel

  {"name": "set_generation_result_favorite", "arguments": {"is_favorite": true, "generation_result_id": 1}}

  Exemple de retour

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

• show_in_shoot_board≈ 337 tokens

  Moves a Shoot Board that is open in a widget to a view (board, brief, automation, results, brief_history). This client shows no widget, so it changes nothing the user sees: read the board, brief or results with read_shoot_board, get_brief or get_generation_results and tell the user.

  Paramètres, retour & exemple (3)

  Paramètres

  • view · string · requis · board | brief | automation | results | brief_history
    board: the board's photos (Clothing, Models, Locations, references, the pinned Automation); brief: the brief's looks beside its automation (once it ran, each look with its photos and videos); automation: the same page, for its automation; results: a brief that ran, at its photos and videos; brief_history: every brief the user ran
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • look_key · string · optionnel
    brief / results: the look to bring forward (a key of the brief's looks)

  Exemple d'appel

  {"name": "show_in_shoot_board", "arguments": {"view": "board", "board_id": "texte"}}

  Exemple de retour

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

• update_brief≈ 1897 tokens

  Use this when the user asks in chat to change the board's brief: its looks, Models, outfits, Locations, references, name, shots and steps, AI model or art direction. Send the complete replacement look list with the brief_id it replaces, keeping each unchanged look's key. Shots or steps: recipe with the complete new shot list (recipe_look_keys for some looks only) or recipe_workflow_id. AI model only: image_model / video_model. Art direction only: art_direction_id. Saves the revised brief on the board; nothing runs. If the result lists problems, fix them all and call again; on revision_conflict, read the board and revise its current brief.

  Paramètres, retour & exemple (10)

  Paramètres

  • looks · array · requis
    The complete new look list (not a diff); an unchanged look keeps its key.
  • title · string · optionnel
    A new name for the shoot, only the user's own words (omit: kept).
  • recipe · ? · optionnel
    The complete new shots and steps, built as a new automation for the looks below (e.g. the old shots plus a side view). Not with recipe_workflow_id.
  • board_id · string · requis
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • brief_id · integer · requis
    The brief being revised: the board's brief_id from read_shoot_board.
  • direction · ? · optionnel
    A new Direction for the whole shoot, replacing the brief's (omit: kept): prompt, art_direction_id (a saved art direction), or both. Write one direction for every look from what the user wants (setting, light, mood, poses, purpose). Never name a garment, model, location or look: the same words run on every look.
  • image_model · string · optionnel
    A listed image model's slug the user asked for ("use GPT Image"): the shoot's AI model, every shot and edit of every look runs on it; the automation is unchanged. Not with recipe (name it in recipe.image_model).
  • video_model · string · optionnel
    A listed video model's slug the user asked for: the shoot's videos run on it. Not with recipe (name it in recipe.video_model).
  • recipe_look_keys · array · optionnel
    The looks (keys you send) that move to recipe / recipe_workflow_id; omit for every look.
  • recipe_workflow_id · string · optionnel
    An automation from read_shoot_board's brief_inputs.automations for the looks below. Not with recipe.

  Exemple d'appel

  {"name": "update_brief", "arguments": {"looks": [], "board_id": "texte", "brief_id": 1}}

  Exemple de retour

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

• update_montage_proposal≈ 1462 tokens

  Patch the latest MontageProposal already shown in the UI. Use only for an existing video montage/reel/stitched sequence proposal; do not use this to modify a photoshoot brief. For photoshoot brief changes, call update_brief instead. Prefer `operations`, an ordered list of typed montage edits such as `clear_trim`, `remove`, `set_duration`, `set_trim_range`, `set_speed`, `set_muted`, `set_prompt`, `set_video_model`, `set_generate_audio`, `set_last_frame`, `set_aspect_ratio`, and `set_base_resolution`. Use `set_trim_range` for requests like 'use the second half', 'start at 3s', or 'trim from 3s to 6s'. Operations are applied in order to the current montage state. Legacy flat fields are still accepted as a compatibility shim. This updates the proposal only; it does not execute export or generation.

  Paramètres, retour & exemple (18)

  Paramètres

  • muted · boolean · optionnel
    Mute or unmute the selected clip(s).
  • speed · number · optionnel
    Playback speed multiplier.
  • prompt · string · optionnel
    Update the motion prompt for image-to-video montage items.
  • remove · boolean · optionnel
    Remove the selected clip(s) from the proposal.
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • end_time · number · optionnel
    Trim end time in seconds for legacy trim-range updates.
  • clear_trim · boolean · optionnel
    For video clips, remove trim bounds and restore the full clip length in the proposal.
  • operations · array · optionnel
    Ordered montage patch operations. Preferred over the legacy flat fields below.
  • start_time · number · optionnel
    Trim start time in seconds for legacy trim-range updates.
  • clip_number · integer · optionnel
    1-based clip number to update. Omit when apply_to_all=true.
  • video_model · string · optionnel
    Update the video model for image-to-video montage items.
  • apply_to_all · boolean · optionnel
    Apply changes to every clip in the current montage proposal.
  • aspect_ratio · string · optionnel
    Update the montage output aspect ratio.
  • clip_numbers · array · optionnel
    Optional list of 1-based clip numbers to update together.
  • generate_audio · boolean · optionnel
    Enable or disable generated audio for image-to-video montage items.
  • last_frame_url · string · optionnel
    Optional last-frame URL for image-to-video montage items.
  • base_resolution · integer · optionnel
    Update the montage output resolution height.
  • target_duration · number · optionnel
    Desired final clip length in seconds.

  Exemple d'appel

  {"name": "update_montage_proposal", "arguments": {"muted": true, "speed": 1, "prompt": "texte", "remove": true, "board_id": "texte", "end_time": 1}}

  Exemple de retour

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

• upload_avatar_from_chat_file≈ 1945 tokens

  Batch upload reusable Models from person photos the user attached in chat. Each photo becomes the upper_body_front identity anchor. Keep names and optional user-given age_range, build, and height_cm in avatars[], then pass top-level image_file_1, image_file_2, etc. in the same order. Traits are never guessed. No base64, no local paths. Do not use ordinary text-to-image results as an upload fallback. Use only when the user explicitly wants a specific or consistent person.

  Paramètres, retour & exemple (20)

  Paramètres

  • name · string · optionnel
    Single recovered avatar/model name
  • build · string · optionnel
    Optional concrete physical build. Never inferred.
  • avatars · array · optionnel
    Avatar/model metadata in the same order as image_file_1, image_file_2, etc. No base64.
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • age_range · string · optionnel
    Optional concrete age or age range. Never inferred.
  • file_name · string · optionnel
    Single recovered original file name
  • height_cm · integer · optionnel
    Optional height in centimeters. Never inferred.
  • image_url · string · optionnel
    Single resolved download URL used by automatic opaque-file recovery.
  • mime_type · string · optionnel
    Single recovered MIME/content type, e.g. image/png
  • description · object · optionnel
    Single recovered avatar metadata
  • image_file_1 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_2 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_3 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_4 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_5 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_6 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_7 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_8 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_9 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.
  • image_file_10 · object · optionnel
    Host-provided uploaded file reference for the matching item index when it has no image_url. Use the file object supplied by the host, not a bare file_... ID.

  Exemple d'appel

  {"name": "upload_avatar_from_chat_file", "arguments": {"name": "texte", "build": "texte", "avatars": [], "board_id": "texte", "age_range": "texte", "file_name": "texte"}}

  Exemple de retour

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

• upload_garment_from_public_url≈ 1390 tokens

  Upload Clothing from public HTTP(S) image URLs. Queues a recoverable batch upload and returns an operation immediately; retry with the exact same arguments to read its state (a retry creates no second upload). Photos are stored as uploaded, without background removal; processing_mode is ignored. Prefer assets with {asset_kind: full|detail, asset_view: front|back|side, asset_url}; exactly one full front is required, every full view is unique, and detail views can repeat. No base64, chat file objects, or local paths.

  Paramètres, retour & exemple (13)

  Paramètres

  • name · string · optionnel
    Single garment name
  • assets · array · optionnel
    Single garment full asset set. Use asset_kind/asset_view. Exactly one full front is required; full views are unique and detail views can repeat.
  • gender · string · optionnel
    Single garment gender: male, female, unisex
  • board_id · string · optionnel
    The open Shoot Board's board_id, from Open Shoot Board or your context.
  • garments · array · optionnel
    Garments to upload from public HTTP(S) URLs. No chat file objects and no base64.
  • file_name · string · optionnel
    Single original file name
  • image_url · string · optionnel
    Single public HTTP(S) front image URL
  • mime_type · string · optionnel
    Single MIME/content type, e.g. image/png
  • description · string · optionnel
    Single item-level garment description hint
  • back_image_url · string · optionnel
    Single optional public HTTP(S) back image URL
  • side_image_url · string · optionnel
    Single optional public HTTP(S) side image URL
  • processing_mode · string · optionnel
    Optional image processing. 'background_removal' removes the background (the platform upload default); 'none' stores the image as-is. Omit to use background removal.
  • detail_image_urls · array · optionnel
    Single optional public HTTP(S) detail image URLs

  Exemple d'appel

  {"name": "upload_garment_from_public_url", "arguments": {"name": "texte", "assets": [], "gender": "texte", "board_id": "texte", "garments": [], "file_name": "texte"}}

  Exemple de retour

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

• uwear_settings_read≈ 156 tokens

  Read the user's saved photoshoot defaults (aspect ratio, camera, resolution) with every allowed value. Backs the plugin settings page.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "uwear_settings_read", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"layout": [], "schema": {}, "values": {}}}

• uwear_settings_update≈ 322 tokens

  Save changed photoshoot defaults (aspect ratio, camera, resolution). Send only the settings that changed; returns every current value. Defaults never authorize a paid generation.

  Paramètres, retour & exemple (1)

  Paramètres

  • set · object · requis

  Exemple d'appel

  {"name": "uwear_settings_update", "arguments": {"set": {}}}

  Exemple de retour

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

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://api.uwear.ai/mcp