MCP App Store
by KeenEthics
Product Videos by Alvin's Club icon

Product Videos by Alvin's Club MCP Server for ChatGPT

By FUTUREVERSE TECHNOLOGIES LLC

Overview

A commerce-native AI agent that makes videos built to sell. Tell it what you're selling and it delivers a finished, ready-to-post short video, with script, AI model, voiceover, caption and hashtags done for you, without filming or editing. It makes shoppable product videos only, not general video content. It is for brands and sellers of clothing, personalized jewelry, chairs and furniture, and also makes model photo lookbooks. Share a product page link (or product photos) and ask for a video: Studio reads the product details and uses the supported category production workflow to make a short vertical video with voiceover on an AI model, and returns a playable link with a ready-to-use caption and hashtags. You can also give a public TikTok video as a reference: Studio borrows its pacing and structure (never its footage, sound or words) for a video of your own product. Supported video lengths and voiceover languages depend on the product category. The current formal apparel limits are listed below; confirm available options before starting. Ask for a lookbook (clothing) and get the product styled on an AI fashion model across several real-world occasions in 1-2 minutes. Everything uses your Alvin's Club Studio account and also appears in your workspace at studio.alvinsclub.ai/app. Before starting a video, ChatGPT tells you what it will use and asks you to confirm. You can check on any video or lookbook by asking whether it is ready. Before you post: check the product matches your listing (colour, print, parts). On TikTok, turn on the 'AI-generated' label. The caption ends with #AlvinsClubStudio; you can remove it. Limitations: Studio makes videos only for the product types listed above, works from public product pages or your own photos, and does not support general social media publishing. When you connect your own LinkedIn account, you can explicitly ask Studio to publish an approved post or video there. The current formal apparel video workflow supports 15-second English videos from public product pages, without a supplied script. An optional public TikTok reference can guide pacing and scene structure through the same formal apparel workflow; its footage, audio and wording are not copied. Requests outside those limits need to be adjusted before starting; Studio does not silently substitute another workflow.

How to connect

  1. ChatGPT: Open the Product Videos by Alvin's Club listing in the ChatGPT app directory and choose Connect. ChatGPT listing Product Videos by Alvin's Club exposes 99 tools here.

Tools

analyze_template_video_reference

ChatGPT
Only after the user explicitly agrees to analyze this saved reference, submit confirmed=true with one stable analysis UUID and the prepared draft revision. The platform pays within its analysis cap. Retry/recover the same original; never generate another ID for an uncertain response. Analysis does not save a private template, approve production or charge the user.

browse_template_candidates

ChatGPT
Save a bounded candidate batch for the current draft inputs. This only reads the catalog, without model analysis. Use one stable batch UUID per requested next batch; retry that UUID after a timeout. Read unseen pages with get_template_candidate_batch at next_offset before requesting another batch.

check_template_video_inputs

ChatGPT
Check one saved selection against the actual version requirements. Explain missing inputs in plain language. Apply explicit subject and saved-material choices in the existing draft, then recheck. A failed check does not establish readiness. This does not approve or create a video.

choose_video_template

ChatGPT
Save the exact catalog template version and the user-selected target mapping. Use a stable item UUID and current draft revision; separate variants need explicit variant intent. Selection is not production approval. Use returned requirements to guide materials, without inventing fixed steps.

classify_company_videos

ChatGPT
Give one or more company videos the same classification (mutually exclusive), exactly as on the videos page. A sub-account may only choose "discarded" (废弃) or "submit_review" (提交审核) for its own videos. The main account, after approving a video, chooses "self_publish" (可自己发布,不提交商家) or "merchant" (提交商家); to discard one it disapproves it with a reason (review_company_video). Pass each video's current revision from list_company_review_videos and one new operation_key per batch (reuse it only to retry the same batch). Only the classification is recorded: nothing is sent, delivered or published. No charge.

confirm_company_creation

ChatGPT
Start exactly the quoted company video after the user clearly agreed to its cost: pass operation_id from the quote and that cost as expected_total_credits. The cost is held from the company budget. decision="reject" declines the quote instead and starts nothing. Never confirm twice or re-quote to recover an uncertain result: read the draft and its operations with get_company_creation_draft.

confirm_product_video_plan

ChatGPT
Create exactly the saved plan using its selected material, at the credits the user explicitly confirmed. Only call after showing the plan and total and receiving confirmation. Repeating the same plan_ref returns the original receipt; it never creates another order. Use get_product_video_plan to check progress/results.

confirm_template_videos

ChatGPT
Only after showing the saved selections, current per-item prices and total and receiving explicit production approval, send confirmed=true with the quoted revision and exact item/quote pairs. Repeated confirmations recover the accepted receipts without another charge. If quotes refresh, show them and ask again. Read each original output for progress; never replace an uncertain order.

connect_linkedin

ChatGPT
Get a link that connects the user's own LinkedIn (needed once, then every 60 days). Give connect_url to the user to open in a browser where they are signed in to Alvin's Club Studio, and allow posting on LinkedIn; then check get_linkedin.

continue_template_video_production

ChatGPT
Continue only an action returned for this original output, after the user explicitly confirms the current proposal. Preserve its attempt/proposal IDs, use one stable operation UUID, and for supplementation use the saved draft revision. Recover the same operation on retry. This cannot authorize an unoffered action or automatically remake a delivered video.

create_advanced_video

ChatGPT
Start the quoted advanced video. Charges the quoted credits: pass exactly the amount the user agreed to. The same quote never makes a second video. Then check get_advanced_video; when it is finished, look at it with inspect_advanced_video before sharing.

create_apparel_video

ChatGPT
Start the quoted apparel selling video. Charges the quoted credits: pass exactly the amount the user agreed to. The same quote never makes a second video. Then check get_product_video with the returned video_id; a video that cannot be made is refunded.

create_custom_model

ChatGPT
Only when the user asks to use their own model (a real person). Paid accounts; costs 10 credits once. Before calling, show the user this one statement and get a clear yes: "I confirm I'm the person in these photos or have their written permission, they're 18 or older and not a public figure, and I agree to use 10 credits (once)." Then call with consent=true (it covers the three consent statements and the charge). image_urls: 1-3 public links to photos of the same person; if the user only has photos in the chat, send them to studio.alvinsclub.ai/app/models to add the model there. Before asking for photos, send the user the example photos at https://studio.alvinsclub.ai/models/photo-guide (what works and what to avoid) and tell them these photo requirements: Photo 1: a close-up of the face and shoulders, facing the camera, eyes open, natural expression. Photo 2: full length, head to feet, standing straight and facing the camera, arms relaxed, in fitted clothes so the body shape shows. Photo 3 (optional): the face from the side, or half length. Only the person who agreed to be your model, alone in every photo: no one else, no mirror selfies. Nothing over the face: no sunglasses, hats, masks or hair across the eyes. Soft, even light (daylight facing a window works); no strong shadows or backlight. A plain, uncluttered background. No filters, beauty retouching or slimming. No text, stickers, logos or watermarks; not a screenshot. Sharp and in focus, at least 1024 x 1024 pixels; JPEG, PNG or WebP, under 4 MB each. Photos are checked (one clearly visible adult, no celebrities, no screenshots); the answer says why if they can't be used.

create_exact_video

ChatGPT
Start the quoted exact replica. Reserves the quoted maximum credits: pass exactly the amount the user agreed to. Accepting the same quote again never makes a second video. Then check get_exact_video with the returned reference.

create_linkedin_post

ChatGPT
Publish a post on the user's own LinkedIn now, with the final text they approved (#words become hashtags). Optionally link_url (a card; title from the page unless link_title) OR media_ids from upload_linkedin_media (one video, or 1-20 photos). For a later or recurring post, use client-side scheduling only if available; this server does not schedule posts.

create_lookbook

ChatGPT
AI stylist lookbook: the product styled on an AI model in real-world scenes, one photo per look (max 8). Each account gets 5 free sets a day; after that a set costs 1 credit: if the answer says so, tell the user the price and their balance, and only with a clear yes call again with accept_charge=true. Give product_url, or image_urls plus product_name; for an outfit give product_urls: 2-4 product pages worn together. looks: styling briefs such as 'Weekend brunch: white sneakers'; omit for 4 default occasions. Keep a chosen model; otherwise omit model_id and let us choose. Only fetch model previews when asked to choose. Photos take 1-2 minutes: then get_lookbook.

create_product_videos

ChatGPT
Create product videos (clothing, accessories, bags, shoes, jewelry, chairs, furniture) after the user confirms the complete recommendation and total credits. Pass product_category (womens_apparel, accessories, bags, footwear, jewelry, seating or furniture) when known; if omitted it is read from the page (the result says which), and when the page doesn't say, nothing is made or charged: ask the user what the product is and call again with it. Default to one 8-second video (3 credits) unless specified. 12 seconds costs +1, 15 +2 each and require a paid account. Do not separately ask for length or model: pick one of our models, or let us choose (omit model_id; for home goods the answer names the model we picked: tell the user once); show model photos only if asked to choose. Pass expected_total_credits and a unique idempotency_key, reused only for the same order. For a new version, read get_video_reuse_options first. Returns immediately: share page_url and actual started/not_started counts. Usually ready in about 10 minutes. Do not promise proactive notifications unless the client supports them. Generated videos are delivered and charged, including edits and home products. Quality warnings do not trigger refunds. use_my_voice=true only when the user asks for their own voice and has set it up at /app/voice (get_account shows has_voice). Voiceover is English unless the user asks for another language: language=es (Spanish), pt-BR (Brazilian Portuguese), de (German), it (Italian), id (Indonesian), ja (Japanese), ko (Korean), zh (Chinese). Spanish & Brazilian Portuguese voiceover: clothing, chairs and furniture for now. The caption and hashtags follow it; same price. Only when the user gives a viral TikTok video to model it on (TikTok links only for now; Instagram and YouTube are not supported yet): pass it as reference_video_url (needs product_url; costs +1 credit per video, include it in the total). We borrow only its structure (pacing, hook, what each shot does) with this product's facts and our model, never its footage, sound, words or creator; passing it means the user confirms they may use that video as a reference (Terms, 'Reference videos'): say so when confirming. replica_mode defaults to swap_product (the video shows another product). Use same_product only when the user says the video already shows THIS product and they want its moves kept; then first get their yes to 'The product in that video is this product, and I have the right to use that video' and pass same_product_confirmed=true. Moves our review never allows are left out and listed on the result. Same-product remakes without duration_seconds are 15 seconds (8 on the free trial; shorter only when the reference's length is known and shorter): quote that price and always pass the confirmed expected_total_credits (it is required then); if the answer says the total changed, confirm the new total. For a product sold in several colors (or styles), pass variant (its name on the product page, e.g. 'Black') only when the user names one; otherwise we pick the one closest to the reference video, else the page's default. Tell the user the color in the answer's product_variant once. For 2-5 garments changing in one video, use outfit_changes in appearance order after product_url. For one garment worn throughout with up to five separately sold outfit items, use styling_products with category tops, bottoms, outerwear, footwear, accessories or bags. These arrays are mutually exclusive. Both modes require a chosen model_id, reference_video_url, womens_apparel, 15 seconds, one English video. Use brief for order/occasion in outfit changes, or styling/placement direction in a styled outfit. Reference cut timing and visible accessory placement are checked before video generation; no equal-time slots or new actions are invented. Confirm the total quoted credits and pass expected_total_credits.

delete_custom_model

ChatGPT
Delete one of the account's own models and its photos, for good.

delete_linkedin_post

ChatGPT
Delete a post made from this account from LinkedIn. Cannot be undone.

disconnect_linkedin

ChatGPT
Disconnect this account's LinkedIn after the user confirms. Already published posts stay on LinkedIn.

edit_linkedin_post

ChatGPT
Replace the text of a published LinkedIn post made from this account.

fix_product_video

ChatGPT
Start the quoted fix. Charges the quoted credits: pass exactly the amount the user agreed to. The new video's video_id is in the result; follow it with get_product_video, then inspect it before sharing.

get_account

ChatGPT
Remaining credits and pricing. Only when asked, or to troubleshoot.

get_adjustment_examples

ChatGPT
How people adjusted this account's advanced videos before (production instructions, picked script suggestions, repair requests). Read once before your first revision; they guide your notes, never facts.

get_advanced_creation_draft

ChatGPT
Read saved inputs and original step status/results after the user saves or returns from the form. Always use the same draft_id, including after a timeout. Does not approve, start, cancel or replace a video. Show business facts, not internal references.

get_advanced_video

ChatGPT
Status of an advanced video or repair (always check again before answering whether it is ready). When finished, share video_url; when video_url_needs_sign_in is true, the user opens it signed in to Alvin's Club Studio.

get_company_creation_draft

ChatGPT
Read saved inputs and original operation/result status after the user returns from the form. Use the same company_id/draft_id; never replace an uncertain order. Does not approve, generate or cancel. Keep internal references out of the user-facing reply.

get_company_creation_options

ChatGPT
Merchants this draft can use and, with project_id, that merchant's products (catalog) and presenters (models). Use the returned ids and names in update_company_creation_draft. Read-only.

get_company_publication_report

ChatGPT
Company main account only: the published videos report for one merchant of this company, the same as its web page. Omit project_id to list the merchants first and ask which one when it is not clear. Optional date_from / date_to (YYYY-MM-DD, company time zone) and platform (tiktok, youtube or instagram). Returns totals, per-creator totals, the most viewed posts with their links, and links to the page and to the Excel / CSV export of every post. Null views, likes, comments or shares are not collected yet: say pending, never zero, and never estimate them. Say how many posts are shown out of posts_total. Read-only.

get_company_video_editor

ChatGPT
Open the original timeline for an existing video, or read the same actor’s saved project after returning. Use version_id from the original video list or export receipt. Saved input is not an export, approval or publication. Never generate a replacement to recover an uncertain edit; keep the original result and use the returned browser link.

get_creation_workspaces

ChatGPT
List company workspaces this account can use for advanced creation. No company is created; personal/simple product creation remains separate.

get_exact_video

ChatGPT
Status of an exact replica (always check again before answering whether it is ready). When finished, share video_url; when video_url_needs_sign_in is true, the user opens it signed in to Alvin's Club Studio. A failed one returns its unused credits.

get_linkedin

ChatGPT
Whether the user's own LinkedIn is connected, as whom, days until it must be reconnected, and today's LinkedIn posts. Check before posting a video to LinkedIn.

get_linkedin_media

ChatGPT
Processing status of an upload (AVAILABLE = ready to post).

get_linkedin_post

ChatGPT
Status of a LinkedIn post (queued, processing, published with linkedin_url, failed).

get_lookbook

ChatGPT
A lookbook's status and its photo links once ready.

get_private_video_template

ChatGPT
Read an owned local template reference from the private catalog. Company reads need its merchant project_id. Keep that source project distinct from the draft target merchant.

get_product_video

ChatGPT
A video's status right now (always call it again before answering "is it ready?"; never answer from memory): reviewing, queued, processing, completed (share video_url, page_url, caption and hashtags), rejected or failed (not charged; for rejected, tell the user the first item of rejection.issues in plain words and offer to order again, with more photos or the product page link; for failed, pass on the error and its next step). Generated videos, including edits and home products, are delivered and charged. Automated quality findings are recorded internally, not presented to the user. Pass on notice if present. If replica.conversion_notice is present, tell the user once (no extra charge: the order continues as is). If model_notice is present, tell the user once. When it is completed, add once: Before you post: check the product matches your listing (colour, print, parts). On TikTok, turn on the 'AI-generated' label. The caption ends with #AlvinsClubStudio; the user can remove it.

get_product_video_options

ChatGPT
Available own/public models, templates and settings for this saved product. Keep current/default choices unless the user wants to change them. Does not start production.

get_product_video_plan

ChatGPT
Recover the saved plan or the original accepted video status/results. After browser editing, read the original reference to get the current plan_ref and choices; show them and get fresh confirmation even when credits are unchanged. A returned browser_url opens the saved product choice editor, not an advanced editor or creation approval. No charge. Query this after a timeout or in a new chat; do not replace the original plan to retry a creation.

get_public_video_template

ChatGPT
Read the exact version returned by the public catalog, including its actual material requirements. Do not infer requirements from the name, example video or another version.

get_recut_video

ChatGPT
Status of a re-cut; when completed, share video_url (the user opens it signed in to Alvin's Club Studio).

get_restaurant_video

ChatGPT
The plan, status and next step of a restaurant video. Status planning -> plan_ready (review it) -> processing (about 15 minutes after the quote is accepted) -> completed with video_url, or failed (any credits charged were refunded). Always check again before saying it is ready.

get_template_candidate_batch

ChatGPT
Read a saved candidate batch without advancing or analyzing it. Omit batch_id to restore the active batch. Follow next_offset even when can_continue is false. After the last page restore next_batch_id or scan if can_continue is true.

get_template_recommendation

ChatGPT
Recover the original recommendation and its status, missing inputs or choices. Preserve its cursor. Do not replace a pending, uncertain or failed analysis with a new ID just to retry.

get_template_reference_analysis

ChatGPT
Read the original owned reference analysis, including its real status, reason and available result. Do not invent progress or treat missing/unknown states as success. No new analysis is requested.

get_template_video_draft

ChatGPT
Restore the original draft and its acknowledged revision. After an uncertain save or browser edit, read this same draft; retain unacknowledged user edits and resolve conflicts before saving again. For visual comparison or uploads, offer the returned browser_url using the same Studio account and company. After the user returns, read this draft again; closing the page is not proof of saving or approval to produce. The link contains no login or production authority.

get_template_video_feedback

ChatGPT
Read feedback for the exact delivered result version. The result_id comes from the original production response; do not substitute another version. This does not request a repair.

get_template_video_production

ChatGPT
Read an original accepted output, actual progress, user actions and retained results. Use the same output_id after a disconnect. Do not infer completion from elapsed time or create another order. Use operation_id to check whether an uncertain continuation or correction was accepted; never automatically resubmit. Only present the original returned authorized result links, never credentials.

get_uploaded_photos

ChatGPT
The photos the user uploaded through a photo upload link: status waiting, uploaded or expired, and image_urls to pass as image_urls to create_product_videos, create_lookbook, inspect_product_link evidence or create_custom_model.

get_video_editor

ChatGPT
Read your original personal video timeline and saved inputs. Use the current video reference or find it in the existing authorized video list. source_kind defaults to video; exact, marketing and edit use references from their original result/editor. After Save editing project, read the SAME reference again. Does not save, export, charge or publish. Company videos use get_company_video_editor. Browser permission is separate from business approval.

get_video_reuse_options

ChatGPT
Read the settings and missing-data warnings for a video on this account. Does not create or charge. For a new version, keep the reusable fields, change only what the user requests, confirm the new cost, then call create_product_videos with a fresh key. Omit warnings when passing creation arguments.

inspect_advanced_video

ChatGPT
Frames of a finished advanced video (as images), its shot cuts and the product photos a repair can use. Free. Compare the frames with the product photos: if a product defect sits in one part (color, shape, a missing or extra part, position), look closer with times_ms and offer quote_advanced_repair. Words on screen, speech or the whole composition cannot be repaired; offer a revised plan instead.

inspect_company_video

ChatGPT
Frames of a finished company advanced video (as images), its shot cuts and the product photos a repair can use. Free. If a product defect sits in one part (color, shape, a missing or extra part, position), tell the user at which seconds and offer quote_company_video_repair. Words on screen, speech or the whole composition cannot be repaired. Frames are never product facts.

inspect_product_video

ChatGPT
Frames of a finished product video (as images), its shot cuts and what a fix of one part costs. Free. Compare the frames with the product photos; if something in one part is wrong (color, an object, the background), tell the user at which seconds and offer quote_video_fix. Words on screen and speech cannot be fixed this way. Frames are never product facts.

list_advanced_creation_drafts

ChatGPT
Find your existing personal advanced drafts by title before starting another one. Use returned draft_id with the original open/get tools. If several drafts match, ask which one the user means; do not pick by recency alone. This only lists saved records, not unsaved browser edits, and never creates or starts work. Follow next_cursor for older results.

list_company_editor_videos

ChatGPT
Find existing videos in the authorized company workspace. Choose by the user’s intended result; ask when several match. Follow next_cursor with before. Read-only: no new video or editor draft is created.

list_company_review_videos

ChatGPT
The company videos this member may see, with their review state, classification and current revision (the main account sees every member's; a sub-account only its own). view="queue" (default) is the review queue, "all" every video; optional project_id (merchant) and review_state. Also returns the rejection reasons for disapprove / request_edit. Follow next_cursor with before. Read-only.

list_examples

ChatGPT
Sample videos and lookbooks with playable links. Show when asked; do not interrupt a complete creation request.

list_fashion_models

ChatGPT
Our AI fashion models and this account's own (custom: true), with preview photos. The user may pick one for lookbooks and videos.

list_linkedin_posts

ChatGPT
LinkedIn posts made from this account, newest first.

list_lookbooks

ChatGPT
This account's recent lookbooks, newest first.

list_private_video_templates

ChatGPT
Read saved templates in this workspace. For a company, use a merchant project the user can access. Never treat a provider version ID as ownership. No analysis or production.

list_product_videos

ChatGPT
This account's recent videos, newest first.

list_public_video_templates

ChatGPT
Browse reviewed templates for the chosen workspace. Show a few choices and their actual requirements. No analysis, production or charge. Preserve opaque cursors. Empty results mean no matching choices, not permission to invent a template. A product link is not a prerequisite.

list_template_recommendations

ChatGPT
Recover this draft's original recommendation requests. Use the returned original analysis IDs after a disconnect or changed draft; listing does not submit a new analysis.

list_template_reference_analyses

ChatGPT
Read this draft's reference analysis history without submitting analysis. Recover the original analysis ID even if the saved reference has since changed.

open_advanced_creation_form

ChatGPT
Open the original personal advanced script and photo form. No generation or charge. Use a stable request_key to create or the original draft_id to reopen. Optional product_intake_ref seeds only a new draft from already saved photos, without re-reading a shop. Optional composition_mode rotation or styling opens the original outfit form instead of the script form. Use company tools for company work. Browser permission is not paid-action approval.

open_company_creation_form

ChatGPT
Return the original browser form and saved draft. No generation or charge. Supply draft_id to reopen; otherwise use a stable request_key of 16–100 characters for retries. Only new drafts use optional project_id. Browser permission does not authorize paid actions.

open_studio_page

ChatGPT
Only for a step the chat cannot do: page='models' (add the user's own model from photos they have on their computer), page='voice' (record their voice), or a browser_url another Studio tool returned (a full form or the saved choice page). Returns url: a one-time link (30 minutes, single use) that signs the user in to this same account and opens that exact page. Give it to the user, wait until they say done, then continue here in the chat. Opening it never charges, generates or publishes anything.

post_video_to_linkedin

ChatGPT
Post one of the user's finished videos to their own LinkedIn now, with text (default: the video's caption and hashtags; #words become hashtags) and visibility PUBLIC or CONNECTIONS. Returns status queued; LinkedIn processes the video for a few minutes, then status published with linkedin_url (get_linkedin_post). For a later or recurring post, use client-side scheduling only if available; this server does not schedule posts.

prepare_product_video

ChatGPT
Save a reviewable plan using the saved product and selected material. Never creates or charges for a video. Reuse idempotency_key for retries; use a new key for changed choices. Show the product, settings and credits before asking the user to confirm. Omit optional choices for defaults.

prepare_template_video_material

ChatGPT
Prepare one original asset already saved in this draft. Use only its owned asset_id and the current revision. After a timeout recover the original draft and retry this same material, not a new upload. Use the returned revision for later checks. No production or charge.

prepare_template_video_reference

ChatGPT
Retain and prepare the reference already saved in this draft at the current revision. Use the returned revision for analysis. This does not approve analysis or create a video.

quote_advanced_repair

ChatGPT
Quote a repair of one part (under 30 s, on shot cuts where possible) of a finished advanced video, with the product photos that show it right. Write the instruction as how the product should look ("the seat and backrest are bare maple wood, as in the photo"), never by naming the thing to remove: a named object can be added instead. Check a shadow or blur is really an object before repairing it. Charges nothing; the original stays as it is. Show the user the part, the fix and the credits, then repair_advanced_video only after a clear yes; inspect the repaired video afterwards.

quote_advanced_video

ChatGPT
Quote one advanced video for the final plan. Charges nothing. Show the user the credits and the plan summary, and only after a clear yes call create_advanced_video with this quote_id and those credits.

quote_company_creation

ChatGPT
Quote the saved draft at its current revision. Returns the operation with its exact cost in company credits and when the quote expires. Nothing is held, charged or started. Tell the user what will be made and the exact cost, and wait for a clear yes.

quote_company_video_repair

ChatGPT
Quote a repair of one part (under 30 s, on shot cuts where possible) of the member's own finished company advanced video, matching the product photos (reference_indices from inspect_company_video). Describe how the product should look, never name the thing to remove. The repaired whole video becomes a new company video; the original stays. Charges and holds nothing; the price is held on the company budget only when accepted. Show the part, the fix and the credits, then repair_company_video only after a clear yes.

quote_exact_video

ChatGPT
Quote an exact replica (mode exact) or an original visual story that follows a reference's structure (mode visual_structure) of a public Instagram Reel or TikTok the user supplied, with one of the account's presenters (model_id from list_fashion_models; omit for the default). Set rights_confirmed only when the user explicitly confirmed they may use that reference, and structure_confirmed only when they chose the original visual story; never infer either. Never invent a reference. This is not a product template remake. Charges nothing: the quote is a maximum; final billing uses the actual cost and unused credits are returned. Show the reference, presenter, length and maximum credits, then create_exact_video only after a clear yes.

quote_restaurant_fix

ChatGPT
After a restaurant video is finished: quote changing one shot (counted from 1) in the user's own words ("shot 2 at St. Lawrence Market in the daytime"). The other shots and the original video stay; a new video is made. Charges nothing; show the credits and only after a clear yes call repair_advanced_video with this quote_id and those credits, then get_restaurant_video with the returned reference.

quote_restaurant_video

ChatGPT
Quote the reviewed restaurant plan (status plan_ready). Charges nothing. Show the credits and the plan, and only after a clear yes call create_advanced_video with this quote_id and those credits.

quote_spoken_line_change

ChatGPT
Quote replacing 1 to 3 seconds of speech in a finished product video with new words in the same voice (a wrong word, name, price or phrase). Confirm the seconds and the exact new words with the user first. It makes a NEW video and keeps the original; the picture does not change; words on screen cannot be changed this way. Charges nothing; show the user the part, the new words and the credits, and say that agreeing also confirms they may reuse the voice heard in that video. Then fix_product_video with this quote_id only after a clear yes.

quote_template_videos

ChatGPT
Prepare current per-item quotes and the total for the selected saved items, including a single item. Show the actual material/choices, prices and total and get explicit production confirmation. Use the returned draft revision and quote IDs. This does not charge or create videos.

quote_video_fix

ChatGPT
Quote a fix of one part (4 to 30 s, starting and ending on shot cuts) of a finished product video. Write how the part should look, never by naming the thing to remove. The fix makes a NEW video and keeps the original. Charges nothing; show the user the part, the change and the credits, then fix_product_video only after a clear yes.

recommend_video_templates

ChatGPT
When the user wants matching recommendations, analyze the saved inputs and returned candidate references within the platform cap. Use one stable analysis UUID and current draft revision; retry that same original after a disconnect, even if later inputs change. No customer charge or video production. A recommendation is a choice to review, not automatic template selection.

recut_restaurant_video

ChatGPT
Free: a new cut of a finished restaurant video from its own clips - another shot order (counted from 1), fewer shots, or another headline (a price in it must be a menu price). The same source, shot order and headline return the first matching version. The video is ready in a minute or two (get_restaurant_video with the returned reference).

rename_video

ChatGPT
Give one of the account's own videos the name the user asked for (shown in their library); an empty name clears it. Only the label changes: the video, its captions and its posts stay as they are. Free.

repair_advanced_video

ChatGPT
Start the quoted repair. Charges the quoted credits: pass exactly the amount the user agreed to. The whole repaired video is delivered as a new video (get_advanced_video with the returned reference).

repair_company_video

ChatGPT
Start the quoted company repair after the user clearly agreed to its credits: pass exactly that amount. It is held and charged on the company budget, never the personal balance; a refusal about company credits or a budget is the company's: relay it as written. Accepting the same quote again never starts a second repair.

repair_template_video_production

ChatGPT
Read the original production first. Only when correction.available is true, explain the selected actual quality checks, correction note and zero additional customer charge, then obtain explicit confirmation. Submit the original result/attempt IDs and one stable operation UUID. The original remaining allowance still controls admission. A new goal, template or creative requirement needs a separately quoted new production; feedback alone does not approve this correction.

review_company_video

ChatGPT
One review decision on a company video, with the same permissions as its page. A sub-account submits ("submit") or withdraws its own video, or discards one never approved. The main account decides: "approve" (with classification "self_publish" or "merchant"), "disapprove" or "request_edit" (both need a reason_code from list_company_review_videos and a reason), "return" or "revoke" (a reason). Pass the current revision and a new operation_key (reuse it only to retry the same decision). Approving records the classification only; it never sends or publishes. No charge.

revise_advanced_plan

ChatGPT
Rewrite the plan's creative direction with your review notes, one change per note (which shot, what is wrong, what it should show). Returns the new prompt and which notes were applied or declined. Free.

save_private_video_template

ChatGPT
After the user reviews and explicitly agrees, save this original analysis as a new private template. A company requires the chosen merchant project_id; an assigned member may save their own analysis. The same analysis recovers the same template. This does not overwrite, publish, select the template for production or start a video; do not supply a forged version or new source.

save_template_video_feedback

ChatGPT
Save the user's feedback against the exact delivered result_id, with one stable operation UUID for retries. Saving feedback does not request a repair, create another video or charge the user.

send_feedback

ChatGPT
Pass the user's feedback to the Alvin's Club Studio team: when they say what they like or dislike about a result or the service, or want to tell us something, offer to send it and use their words (never invent it). rating: 'up' or 'down' if they gave one; video_id / lookbook_id when it is about one result.

update_company_creation_draft

ChatGPT
Save changed fields of the saved draft: project_id, sku_name, model_id, prompt (the brief), duration, language, video_name and the other text or choice fields shown in its inputs. Pass the draft's current revision as expected_revision and a new edit_key (16-100 letters, digits, - or _) per change; reuse the key only to retry the same change. Photos and files are added by the user on the form (browser_url). No generation or charge.

upload_linkedin_media

ChatGPT
Upload a photo (JPG/PNG/GIF up to 10 MB) or an MP4 (up to 200 MB) from a public https link to LinkedIn, for create_linkedin_post. A video needs a few minutes: check get_linkedin_media until status is AVAILABLE.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/alvin-s-club-studio"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/alvin-s-club-studio)