MCP tool reference

list_designsmcp:read

List designs for the current team, with optional folder filter and pagination.

Arguments

Returns

An object with designs: [{id, title, folderId, brandProfileId, createdAt, updatedAt}]. Up to limit results.

Example

{"jsonrpc":"2.0","method":"tools/call","id":1,
 "params":{"name":"list_designs","arguments":{"limit":10}}}

get_designmcp:read

Fetch full metadata for a single design including title, folder, brand profile references and creation date.

Arguments

Returns

An object with full design metadata: id, title, folderId, brandProfileId, createdAt, updatedAt and any associated provider data.

Example

{"jsonrpc":"2.0","method":"tools/call","id":2,
 "params":{"name":"get_design","arguments":{"designId":"<id>"}}}

search_designsmcp:read

Full-text search across design titles and descriptions for the active team. Filters: limit (1-100, default 20).

Arguments

Returns

An object with designs: [{id, title, folderId, snippet, updatedAt}]. Snippet contains matching context.

Example

{"jsonrpc":"2.0","method":"tools/call","id":3,
 "params":{"name":"search_designs","arguments":{"query":"logo","limit":10}}}

list_brand_profilesmcp:read

Return all brand profiles for the current team with voice, themes, niche and industry fields.

Arguments

No arguments.

Returns

An object with profiles: [{id, name, brandVoice, mainThemes, primaryNiche, industry, isActive}].

Example

{"jsonrpc":"2.0","method":"tools/call","id":4,
 "params":{"name":"list_brand_profiles","arguments":{}}}

list_foldersmcp:read

List folders in the active team workspace. Useful for targeting list_designs to a specific folder.

Arguments

No arguments.

Returns

An object with folders: [{id, name, designCount, createdAt}].

Example

{"jsonrpc":"2.0","method":"tools/call","id":5,
 "params":{"name":"list_folders","arguments":{}}}

list_photo_packsmcp:read

Browse available photo packs. Accepts an optional language parameter to filter category labels.

Arguments

Returns

An object with packs: [{id, name, category, imageCount, language}].

Example

{"jsonrpc":"2.0","method":"tools/call","id":6,
 "params":{"name":"list_photo_packs","arguments":{}}}

list_teamsmcp:read

Return the teams the authenticated user owns or belongs to, with the currently active team flagged.

Arguments

No arguments.

Returns

An object with currentTeamId and teams: [{teamId, teamName, isCurrent}].

Example

{"jsonrpc":"2.0","method":"tools/call","id":7,
 "params":{"name":"list_teams","arguments":{}}}

get_plan_limitsmcp:read

Read the current subscription tier and per-tier quotas (storage and AI credits). The aiCredits bucket nests monthly subscription credits, purchasedBalance from one-off credit packs, total ceiling, and remaining available. Useful before mutating tools to predict whether the call will succeed.

Arguments

No arguments.

Returns

An object with tier, isPaid, isTrial, upgradeUrl, limits.storage ({limit, current, exceeded}), limits.aiCredits ({monthly:{limit,current,exceeded}, purchasedBalance, total, available}), and creditsAvailable ({monthly, purchasedBalance, total}). For ULTRA Unlimited, limits.aiCredits.monthly.limit and limits.aiCredits.total are both -1, limits.aiCredits.available is null, and creditsAvailable.monthly and creditsAvailable.total are both null. purchasedBalance is always a number (zero when no packs).

Example

{"jsonrpc":"2.0","method":"tools/call","id":8,
 "params":{"name":"get_plan_limits","arguments":{}}}

get_planmcp:read

Read plan name, billing cycle (monthly or yearly), Stripe subscription status, currency, renewal date, trial end, and seat count. Pairs with get_plan_limits which returns quota usage. Available on every plan with no AI credit cost.

Arguments

No arguments.

Returns

An object with tier, isPaid, isTrial, billingCycle (monthly or yearly or null) and status (Stripe subscription status). It also has currency, renewalDate (ISO 8601), trialEnd (ISO 8601 or null), quantity (seat count or null), cancelAtPeriodEnd and upgradeUrl.

Example

{"jsonrpc":"2.0","method":"tools/call","id":43,
 "params":{"name":"get_plan","arguments":{}}}

search_toolsmcp:read

Search the MCP tool catalog by free-text query, category, or intent. Returns categories, requiresScope, one-line descriptions, and matched use-case tags. Free for all plans (discovery surface).

Arguments

All optional. Call with no arguments to list every available tool.

Returns

An object with totalTools, matchCount, categories: [string[]], and tools: [{name, category, requiresScope, description, useCases, matchedOn: [name|category|description|use_case]}].

Example

{"jsonrpc":"2.0","method":"tools/call","id":9,
 "params":{"name":"search_tools",
           "arguments":{"query":"brand profile"}}}

create_avatarmcp:writePaid plan

Generate an AI avatar image from a text prompt. Returns a URL to the generated image and the task ID. Requires AI credits and a paid plan.

Arguments

Returns

An object with taskId, status, imageUrl (when ready), and creditsUsed.

Example

{"jsonrpc":"2.0","method":"tools/call","id":10,
 "params":{"name":"create_avatar",
           "arguments":{"prompt":"professional headshot, warm lighting"}}}

set_current_teammcp:write

Switch the active team for this Bearer token. The user must be a member. Persisted on the OAuth token; in-session mutation makes it effective immediately for subsequent tools in the same conversation.

Arguments

Returns

An object with teamId, teamName, persisted (true if OAuth, false if API key) and an optional note.

Example

{"jsonrpc":"2.0","method":"tools/call","id":11,
 "params":{"name":"set_current_team",
           "arguments":{"teamId":"team_xxxxx"}}}

update_brand_profilemcp:write

Patch the active brand profile. Allowed fields: brandVoice, mainThemes, contentGoals, contentTypes, primaryNiche, subNiches, industry, industries. Anything else is silently dropped.

Arguments

Other patchable fields: mainThemes, contentGoals, contentTypes, primaryNiche, subNiches, industry, industries.

Returns

An object with profileId, name, updated: [field names that were patched], and the current values of brandVoice, mainThemes, contentGoals, contentTypes, primaryNiche, industry after the patch.

Example

{"jsonrpc":"2.0","method":"tools/call","id":12,
 "params":{"name":"update_brand_profile",
           "arguments":{"brandVoice":["bold","minimal"]}}}

list_avatarsmcp:read

List avatar generation tasks for the current user (user-scoped, not team-scoped). Optional status filter and limit (default 50, max 100).

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":13,
 "params":{"name":"list_avatars","arguments":{"status":"completed"}}}

get_avatarmcp:read

Retrieve full detail for a single avatar task by taskUUID. Returns task state including generated images when complete. Cross-team access is rejected when teamId is resolved.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":14,
 "params":{"name":"get_avatar","arguments":{"taskUUID":"<uuid>"}}}

get_avatar_statusmcp:read

Poll an avatar task progress. Returns a slim status snapshot (status, progress, message). Use get_avatar to retrieve full detail including generated images once complete.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":15,
 "params":{"name":"get_avatar_status","arguments":{"taskUUID":"<uuid>"}}}

list_assetsmcp:read

List assets (uploaded images, videos and files) for the active team. Optional filters by folder or MIME-type prefix. Use get_asset for full detail.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":18,
 "params":{"name":"list_assets","arguments":{"type":"image","limit":20}}}

get_assetmcp:read

Retrieve full detail for a single asset by ID. Cross-team access is rejected by the underlying service.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":19,
 "params":{"name":"get_asset","arguments":{"id":"<assetId>"}}}

list_brand_assetsmcp:read

List brand assets (logos, fonts, palette swatches and similar) for the active team. Optional filters by brand profile, file type, category, tags or free-text search. Distinct from brand profiles, which describe voice and themes.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":20,
 "params":{"name":"list_brand_assets","arguments":{"category":"logo"}}}

generate_imagemcp:writePaid plan

Generate one or more AI images synchronously (about 30 seconds). The credit cost depends on the model. FREE tier is blocked. Pass clientRequestId for idempotent retries within 5 minutes. Returns the generated image URLs immediately.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":21,
 "params":{"name":"generate_image",
           "arguments":{"prompt":"sunset over the alps","aspectRatio":"16:9"}}}

generate_videomcp:writePaid plan

Submit an AI video generation task. Returns a taskUUID immediately; the task is processed asynchronously (BullMQ-backed). Use get_video_status to poll for completion. Credit cost is calculated from model and duration. FREE tier is blocked.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":22,
 "params":{"name":"generate_video",
           "arguments":{"prompt":"a cat surfing","model":"<videoModelId>"}}}

get_video_statusmcp:read

Poll a video generation task progress. Returns full task state including the final video URL when complete. Backed by a BullMQ queue (real async).

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":23,
 "params":{"name":"get_video_status","arguments":{"taskUUID":"<uuid>"}}}

search_stock_photosmcp:read

Search stock photos across Unsplash, Pexels and Pixabay simultaneously. Returns results from each provider plus any per-provider errors. Search-only; no list or browse.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":24,
 "params":{"name":"search_stock_photos","arguments":{"query":"mountains"}}}

list_community_workflowsmcp:read

List published community workflows. Filter by category, sort by popular, recent or views, and scope to mine, team or all. Use get_community_workflow for the full graph.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":25,
 "params":{"name":"list_community_workflows","arguments":{"sort":"recent"}}}

get_community_workflowmcp:read

Retrieve full detail for a community workflow including its node graph and edges. Use list_community_workflows for browsing.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":26,
 "params":{"name":"get_community_workflow","arguments":{"id":"<workflowId>"}}}

list_pipelinesmcp:read

List pipelines (workflow canvases) for the active team. Returns slim shape with node counts; use get_pipeline for the full graph.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":27,
 "params":{"name":"list_pipelines","arguments":{}}}

get_pipelinemcp:read

Retrieve a pipeline (workflow canvas) by ID, scoped to the active team. Returns the full node and edge graph.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":28,
 "params":{"name":"get_pipeline","arguments":{"id":"<pipelineId>"}}}

list_whiteboardsmcp:read

List MySpace whiteboards for the current user, scoped to the active team. Whiteboard content is omitted from the list view; use the dedicated read endpoint for content.

Arguments

No arguments.

Example

{"jsonrpc":"2.0","method":"tools/call","id":29,
 "params":{"name":"list_whiteboards","arguments":{}}}

list_conversationsmcp:read

List the user's chats inside the DesignerBox app for the active team. Optional status filter (active or archived) and tag filter. Use get_conversation for the full message history.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":30,
 "params":{"name":"list_conversations","arguments":{"status":"archived"}}}

get_conversationmcp:read

Retrieve a single chat from the DesignerBox app, including its full message history. The service rejects a request for another user's or another team's chat.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":31,
 "params":{"name":"get_conversation","arguments":{"id":"<conversationId>"}}}

generate_designmcp:writePaid plan

Generate a gallery design by applying a skill to a source image (image-to-image). Synchronous, about 30 to 45 seconds. The call charges credits. FREE tier is blocked. Use list_skills to discover valid skillId values. Pass clientRequestId for idempotent retries within 5 minutes.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":32,
 "params":{"name":"generate_design",
           "arguments":{"sourceImageUrl":"https://example.com/photo.jpg","skillId":"<skill>"}}}

list_galleriesmcp:read

List AI gallery assets (designs generated via generate_design) for the active team and user. Supports pagination and an optional category filter. Returns a slim shape: assetId, assetUrl, slug, displayName, galleryCategory, createdAt.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":33,
 "params":{"name":"list_galleries","arguments":{"limit":10}}}

list_skillsmcp:read

List active skills available for generate_design. Returns skillId, name, type (image or video), group and category. Use this to discover valid skillId values before calling generate_design.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":34,
 "params":{"name":"list_skills","arguments":{"type":"image"}}}

generate_cinema_studiomcp:writePaid plan

Generate cinematic AI images using a camera body, lens, focal length, aperture and aspect ratio combination. Synchronous, about 30 seconds. The credit cost depends on the model. FREE tier is blocked. Supply referenceImageUrl to switch to reference-image (style-transfer) mode. Pass clientRequestId for idempotent retries within 5 minutes.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":35,
 "params":{"name":"generate_cinema_studio",
           "arguments":{"scenePrompt":"a wide shot of a foggy harbour at dawn","aspectRatio":"16:9","imageCount":2}}}

cancel_avatar_taskmcp:writeDestructive

Cancel a pending or in-flight avatar generation task. The service-side refund path returns previously-charged credits. Terminal-state tasks (completed or failed) cannot be cancelled; the call surfaces a structured error.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":36,
 "params":{"name":"cancel_avatar_task","arguments":{"taskUUID":"<uuid>"}}}

cancel_video_taskmcp:writeDestructive

Cancel a pending or in-flight video generation task. The service-side refund path returns previously-charged credits. Terminal-state tasks (completed or failed) cannot be cancelled; the call surfaces a structured error.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":37,
 "params":{"name":"cancel_video_task","arguments":{"taskUUID":"<uuid>"}}}

list_video_tasksmcp:read

List video generation tasks for the current user (user-scoped, parity with list_avatars). Optional status filter (pending, processing, completed, failed, cancelled) and limit (default 20, max 100). Use get_video_status for full polling detail.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":38,
 "params":{"name":"list_video_tasks","arguments":{"status":"completed"}}}

get_brand_profilemcp:read

Retrieve full detail for a single brand profile by ID. Cross-team access is rejected with a generic not-found (no existence leak). Use list_brand_profiles to enumerate IDs.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":39,
 "params":{"name":"get_brand_profile","arguments":{"brandProfileId":"<uuid>"}}}

get_brand_assetmcp:read

Retrieve full detail for a single brand asset by ID. Cross-team access is rejected with a generic not-found (no existence leak). Use list_brand_assets to enumerate IDs.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":40,
 "params":{"name":"get_brand_asset","arguments":{"brandAssetId":"<uuid>"}}}

get_photo_packmcp:read

Retrieve a single photo-pack category including its images. Catalog-shaped (not team-scoped). Optional language code; falls back to English when the requested locale is missing.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":41,
 "params":{"name":"get_photo_pack","arguments":{"categoryId":"3d-rendered-object"}}}

get_whiteboardmcp:read

Retrieve a single whiteboard by ID including its full content blob. Whiteboards are user-scoped (creator-only); cross-user access is rejected with a generic not-found.

Arguments

Example

{"jsonrpc":"2.0","method":"tools/call","id":42,
 "params":{"name":"get_whiteboard","arguments":{"whiteboardId":"<uuid>"}}}

delete_designmcp:writeDestructive

Delete a design. Your client asks you first.

Arguments

delete_assetmcp:writeDestructive

Delete a picture or a video from Assets.

Arguments

edit_imagemcp:write

Change one part of a picture and hold the rest.

Arguments

Returns

The answer includes creditsCharged, the credits the edit charged.

apply_image_templatemcp:write

Run a template by name, with your photo.

Arguments

Returns

The answer includes creditsCharged, the credits the run charged. The template's prompt is never returned.

remove_backgroundmcp:write

A transparent PNG of the product.

Arguments

Returns

The URL of a PNG with a transparent background.

photo_anglesmcp:write

A new camera angle of the same product.

Arguments

spotlightmcp:write

Relight a photo: direction, type, brightness, colour.

Arguments

flat_laymcp:write

One flat lay from several product photos.

Arguments

product_admcp:write

An ad picture from a product photo.

Arguments

virtual_try_onmcp:write

A garment worn by the person in your photo.

Arguments

skin_retouchmcp:write

Clean skin, with the pose and background kept.

Arguments

fashion_videomcp:write

A fashion clip that keeps the outfit.

Arguments

Returns

A taskUUID. The video runs in the background. Check it with get_video_status.

styled_scenemcp:write

A scene by city, season and time of day.

Arguments

create_video_projectmcp:write

A timeline: clips, titles, sound and a look.

Arguments

Returns

The id of the new video project. The call does not render the video and charges no credits.

render_video_projectmcp:write

Turn the timeline into one MP4 file.

Arguments

Returns

The call answers immediately. The render takes about one to five minutes. Check it with get_video_render_status.

get_video_render_statusmcp:read

The MP4 when the timeline is finished.

Arguments

Returns

The URL of the finished MP4 when the render is done. The error when the render failed.

delete_video_projectmcp:writeDestructive

Delete a timeline you no longer need.

Arguments

run_pipelinemcp:write

Run a workflow and read every step's result.

Arguments

Returns

The results of every step: pictures, videos or text. The call waits until the run is finished, up to about eight minutes.

create_pipelinemcp:write

Save a new workflow in the workspace.

Arguments

Returns

The id of the new workflow. The call saves the workflow and does not run it.

update_pipelinemcp:write

Change the steps of a workflow you have.

Arguments

delete_pipelinemcp:writeDestructive

Delete a workflow from the workspace.

Arguments

run_appmcp:write

Run an app with its form fields filled.

Arguments

Returns

A runId. The run continues in the background. Check it with get_app_run.

get_app_runmcp:read

How far a run has gone, then its results.

Arguments

Returns

The status of the run, its progress (completed, total and percent) and any error. When the run is finished, the result pictures.

create_designmcp:write

Save a Studio design, up to twenty pages.

Arguments

Returns

The id of the new design. You can open the design in the Studio editor. The call does not render a picture.

create_brand_profilemcp:write

Add a brand profile: name, voice, themes, industry.

Arguments

set_default_brand_profilemcp:write

Pick which brand profile is the team default.

Arguments

talking_avatarmcp:write

A face that reads your script or your audio.

Arguments

Returns

A requestId, immediately. The video takes about one to three minutes. Check it with get_talking_avatar_status. The answer includes creditsCharged.

get_talking_avatar_statusmcp:read

The lipsync clip when it is ready.

Arguments

Returns

The status of the job. When the job is done, the URL of the finished video.

list_image_templatesmcp:read

The template catalogue, searchable.

Arguments

Returns

A page of template cards. Each card has an id, a slug, a title, hashtags and preview pictures. The prompt is not included.

get_image_templatemcp:read

One template with its model and its size.

Arguments

Returns

The preview pictures, the title, the description and the hashtags, plus the model, the aspect ratio and the size the template uses. The prompt is not returned.

list_image_modelsmcp:read

Image models, with what each one costs.

Arguments

Returns

For each model: its id, what it can do, the aspect ratios it supports and its credit cost per image.

list_video_modelsmcp:read

Video models, with durations and cost.

Arguments

Returns

For each model: its id, what it can do, the durations and resolutions it allows and its credit cost per second.

import_chat_imagemcp:write

Pictures you attach to a message, saved to Assets.

Arguments

upload_assetmcp:write

A file picker in the chat. The file lands in Assets.

Arguments

No arguments.

Returns

The URL of the file you added. Pass it as the picture to apply_image_template, edit_image or generate_design.