Dreambooth Studio
Server Details
Ask about your Dreambooth Studio photobooths: sessions, revenue, credits, projects, device status.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Dreambooth-Studio/dreambooth-mcp
- GitHub Stars
- 0
- Server Listing
- dreambooth-mcp
- ChatGPT
- Dreambooth Studio
- Claude
- –
TDQS
Scored across 22 tools
Boundaries between adjacent tools are spelled out explicitly (start_booth vs duplicate_project, get_revenue_summary vs get_wallet_transactions, get_sessions vs get_gallery_stats, start_frame vs start_booth), so misselection is unlikely. The only soft spots are check_generation vs get_booth_draft (job status vs draft read) and connect_account vs connection_status, but the descriptions disambiguate both with an explicit 'use this when' rule.
Almost every tool follows a clear verb_noun pattern (start_frame, refine_booth, save_frame, get_project, list_projects, update_booth_draft) with get/list/start/refine/create/duplicate families. The single outlier is connection_status, a noun phrase with no verb, which breaks the pattern slightly but remains readable.
At 22 tools this is on the heavy side of the recommended range, but the surface spans genuinely separate sub-domains (frame design, booth design/creation, filters, booth analytics, revenue, credits, docs, account) and no tool looks redundant or decorative. Each one earns its place; the count is defensible rather than padded.
The draft lifecycle is fully covered (start → refine → update → create → poll), but there are real dead ends the tools themselves admit: no edit or delete for booths, frames, or filters, and no way to list existing frames or filters so an agent can reference one by id. Those gaps are deliberate (the dashboard owns them), yet they will force the agent to hand off mid-task, which is more than a minor workaround.
Available Tools
22 toolscheck_generationCheck background workARead-onlyIdempotentInspect
Report on background work started by start_frame, refine_frame, start_booth, refine_booth or create_booth. Always pass the jobId that the start/refine/create call returned — keep it for the rest of the conversation, because an id keeps working for the full 15 minutes even if the connection re-authenticates partway through, and calling with no arguments does not. With no arguments it reports the most recent job of any kind, which is a convenience for when the id was lost, not the normal way to call it. Designing a booth takes 1-3 minutes, a redraw about a minute, creating a booth 2-6 minutes: tell the operator that, then poll about every 15 seconds. While it says 'running', nothing exists yet — relay the progress line if there is one, tell the operator it is still going, and wait 10-15 seconds before calling again rather than polling tightly. When it says 'done': a frame job carries imageUrl, threadId and generationId (a preview — nothing saved until save_frame); a booth design carries draft{…} (a draft — nothing created until create_booth); a booth creation carries booth{slug, boothUrl, projectId} — the one case where something now exists. This reads a status and creates nothing, so it is always safe to call.
Inputs: jobId. Returns: kind, note, what, booth, +13 more
connect_accountConnect a Dreambooth accountAInspect
Connect this conversation to the person's Dreambooth Studio account. The answer's status says what happened. already_connected: an account is connected; nothing to do. awaiting_approval: it returns a link the person opens in their own browser to sign in with Google and approve. A Google account with the same email as an existing Dreambooth account connects that account. Ask them to open it and say when they are done; do not call this tool again while waiting. use_client_sign_in: this client connects accounts through its own app or connector settings, where they can sign in with an email and password or with Google, so no link is returned. Ask them to connect Dreambooth there (the client also asks by itself when a tool needs an account), then repeat their question. Either way, someone who has no Dreambooth account yet gets one when they sign in. Call this when another tool reports that no account is connected, or when someone asks to connect or switch accounts.
Inputs: no named parameters. Returns: email, status, authUrl, message, +2 more
connection_statusCheck Dreambooth connectionARead-onlyIdempotentInspect
Whether this conversation currently has a Dreambooth account connected, and which one. Call this if you are unsure whether to run connect_account first. Cheap and read-only — it does not contact Dreambooth.
Inputs: no named parameters. Returns: email, phase, message, connected, +1 more
create_boothCreate the boothAInspect
Create the booth from a finished draft — the step that makes something real, live at its public link. Call it only after the operator has seen the draft via check_generation and agreed to create it; the title and link name (slug) default to the draft's unless the operator chose others. It reads the draft first (so everything set with update_booth_draft — settings, frames, filters, AI effect — is carried), checks the link name, draws the booth's own three photo-strip frames (3 images, up to five minutes), adds three starter frames from the catalogue and the Studio's default 'Normal' filter the way dreambooth.app/new does, then creates the booth with the draft's welcome design, background, colour theme and capture mode. Frames saved with save_frame and filters made with create_filter on this connection are carried automatically; ids can also be passed. Tell the operator it takes 2-6 minutes. Returns a job id; check_generation reports progress and, when done, the booth's public link, id and a dashboard link. If the link name is taken it stops before drawing anything — ask for another and call again. Creating twice with different link names makes two booths. The booth is live (unlisted) at once; there is no tool that edits or deletes a booth — changes happen in the dashboard.
Inputs: draftId (required), slug, title, frameIds, +3 more. Returns: kind, note, slug, what, +4 more
create_filterCreate a photo filterAInspect
Create a new photo filter on this operator's account from a description of the look they want — 'warm and slightly faded', 'high contrast black and white'. Translate the description into the adjustment numbers yourself; the ranges are in the schema. Call this only when the operator asks for a filter to be CREATED. It does not change an existing filter, and there is no tool that does — to edit or delete one, send them to the dashboard. Creating the same filter twice makes two filters, so do not retry a call that may have gone through.
Inputs: name (required), adjustments (required), isPublic. Returns: id, kind, name, isPublic, +3 more
duplicate_projectDuplicate a boothAInspect
Copy one of this operator's existing booths, with all of its settings, into a new one. Use it when they want another booth 'like' one they already run — a second location, a one-off event, a variant to experiment on. Call list_projects first to get the project id; the operator will name the booth, not its id. The copy is named after the original and is not published at the original's public address, so it is safe to make and they can rename it in the dashboard. To design a NEW booth from a description, use start_booth instead of this; there is no tool that edits or deletes a booth that already exists.
Inputs: projectId (required). Returns: id, kind, slug, title, +3 more
get_booth_draftRead a booth draftARead-onlyIdempotentInspect
Read a booth draft by its draftId — the same summary check_generation gives for a finished design, plus everything the draft has been given since (settings, chosen frames, filters, AI effect). Use it when the job from start_booth is no longer tracked, to show the draft again before create_booth, or to confirm what update_booth_draft applied. Reads only; nothing is generated or created. A draft lives 7 days on the operator's account.
Inputs: draftId (required). Returns: kind, note, what, draft, +4 more
get_creditsGet AI credits and planARead-onlyIdempotentInspect
This operator's remaining AI credit balance and their current subscription plan, including when it ends. Call this when they ask how many credits are left, whether they can still run AI effects, or what plan they are on. Credits are separate from wallet money — do not confuse the two.
Inputs: no named parameters. Returns: plan, credits, videoCredits, sessionCredits, +1 more
get_gallery_statsGet gallery statisticsARead-onlyIdempotentInspect
How much media this operator's booths have produced: total, still active, and expired past the retention window. Call this when the operator asks how many photos or videos a booth has taken, or whether media is being lost to retention. Returns counts only, not the media itself.
Inputs: projectId, includeExpired. Returns: totalCount, activeCount, expiredCount
get_projectGet one booth in detailARead-onlyIdempotentInspect
Full detail for a single booth: its name, public link, currency, screen size, and the live status of the device running it — whether it is online, when it was last seen, app version, and camera/printer/internet state. Call this when the operator asks about one specific booth, or whether a booth is working. Get the project id from list_projects first.
Inputs: projectId (required). Returns: devices, project, deviceCount
get_revenue_summaryGet revenue summaryARead-onlyIdempotentInspect
Business revenue from this operator's photobooth sessions across EVERY payment channel — gateway payments, cash vouchers (cash collected at the booth) and discount vouchers — grouped by month or day and by currency, with extra-print revenue and AI-effect purchases reported separately. Use this for any question about income, revenue or omzet. It is also the right tool when wallet earnings look too small: cash and voucher money never reaches the wallet ledger, so for operators who take cash the wallet figure legitimately understates income.
Inputs: to, from, groupBy. Returns: to, from, found, source, +5 more
get_sessionsGet photo sessionsARead-onlyIdempotentInspect
List the photo sessions recorded on this operator's booths, with totals. Call this when the operator asks how busy a booth has been, how many sessions ran in a period, or wants to inspect individual sessions. Supports date ranges, per-booth filtering, payment status and payment channel. For money totals rather than session counts, use get_revenue_summary instead.
Inputs: limit, endDate, startDate, projectIds, +3 more. Returns: total, returned, sessions, totalPages
get_wallet_transactionsGet wallet transactionsARead-onlyIdempotentInspect
This operator's wallet ledger: gateway earnings, withdrawals and refunds, newest first. Use for questions about the wallet, payouts or withdrawals. Do NOT use it to answer 'how much did I earn' — the wallet excludes cash and voucher income entirely, so for operators who take cash it understates real revenue. Use get_revenue_summary for income.
Inputs: to, from, limit. Returns: total, returned, truncated, transactions
list_projectsList boothsARead-onlyIdempotentInspect
List the photobooth projects this operator owns, with id, name, public link slug, whether it is active, and its currency. Call this first whenever the operator names a booth — you need the project id to filter any other tool by booth. Does not return booth designs or page layouts.
Inputs: no named parameters. Returns: count, projects
preview_filterPreview a photo filterARead-onlyIdempotentInspect
Show what a filter would look like BEFORE creating it: the Studio renders its sample photo (or the operator's own preview photo, if they set one in the dashboard) through the exact pipeline the booth uses, and returns an image URL. Free and read-only — call it whenever the operator is designing a filter, adjust the numbers from their reaction ('warmer', 'less contrast'), preview again, and call create_filter with the same adjustments only once they are happy. Some adjustments (shadows, highlights, whites, blacks, clarity, dehaze, vibrance, texture) are applied by the booth but cannot be shown here; the result lists them as notPreviewed so you can say so. Nothing is created by this tool.
Inputs: adjustments (required). Returns: kind, note, sample, previewed, +3 more
refine_boothRefine a booth draftADestructiveInspect
Change a booth draft from start_booth, using the draftId check_generation returned. what='welcome' redraws the welcome screen from an instruction ('warmer colours', 'bigger headline', 'less clutter') while keeping the design; add orientation 'phone' or 'laptop' to redraw only that screen (1 redraw) — without it both screens are redrawn (2). To change the words on the welcome screen (the couple's names, a new headline), pass headline with the exact new words: it is stored on the draft and both screens are repainted with it (2 redraws). Never use orientation for that, or the phone and laptop screens say different things. what='app-background' redraws the calmer backdrop behind the rest of the booth (1 redraw). what='everything' rebuilds the whole draft from a NEW full description (spends 1 of the draft's 3 full generations) — only when the operator wants a different booth, not a tweak. A draft has 5 redraws in total; check_generation reports what is left. Title, headline, link name and colours cannot be edited directly: they change only through a redraw instruction, or at create time (title, slug). Returns a job id; call check_generation. Call only when the operator asks for a change — never iterate on your own.
Inputs: what (required), draftId (required), instruction (required), headline, +1 more. Returns: kind, note, what, error, +3 more
refine_frameRefine a photo frame designAInspect
Ask for a changed version of a frame in an existing design thread — 'darker', 'less ornament', 'make the flowers smaller', 'more gold'. Call it with the threadId that check_generation returned for start_frame, and ONLY when the operator asks for a change: every call spends part of the account's free daily allowance, so never iterate on your own initiative. It returns immediately with a job id; call check_generation for the new preview. Earlier versions in the thread stay available to save_frame, so a change the operator dislikes loses nothing.
Inputs: prompt (required), threadId (required). Returns: kind, note, what, error, +3 more
save_frameSave a generated frameAInspect
Save one generation from a design thread as a real frame in this operator's frame list, with its photo windows cut out. Call it only when the operator has chosen a result — pass the threadId and generationId that check_generation returned for it. This CREATES a frame: saving the same generation twice makes two frames, so do not retry a call that may have gone through. The frame is private to the account unless the operator explicitly asks for it to be shared. After saving, the operator picks the frame in a booth's frame settings; this tool does not assign it to a booth, and there is no tool that edits or deletes a frame.
Inputs: threadId (required), generationId (required), name, isPublic. Returns: kind, name, state, frameId, +8 more
search_docsSearch Dreambooth documentationARead-onlyIdempotentInspect
Search the Dreambooth Studio documentation and FAQ. Call this before answering any question about the product, hardware, printing, booth setup, guest payments, or troubleshooting — answer from the docs rather than from memory. Pages about Dreambooth's own plans and billing come back as a link only: share the link, and do not quote prices, plans or trials in the conversation. Works without a connected account.
Inputs: query (required), limit, locale. Returns: query, locale, results, resultCount
start_boothDesign a new boothAInspect
Design a complete photobooth (a 'booth') for this operator from a description — the Studio designs the welcome screen for phone and laptop, the in-booth background, the colour theme, the capture mode, a title and a link name, exactly as dreambooth.app/new does. Before calling, gather in chat what /new would ask and put ALL of it in the prompt: the occasion or business, the vibe or style, colours, and the language the booth should speak — there is no separate questions step. It returns a job id immediately; call check_generation, and do NOT describe the booth as designed or created until that says done. The result is a DRAFT with a draftId: nothing is in the operator's booth list until create_booth. Every call makes a new draft and spends 1 of its 3 full generations, and an account may start 10 drafts an hour — never call it speculatively or twice for one request; change a draft with refine_booth instead.
Inputs: prompt (required), language. Returns: kind, note, what, error, +2 more
start_frameStart designing a photo frameAInspect
Start designing a new photo frame for this operator's booths from a description of the look they want — 'batik motifs in warm gold', 'minimal Scandinavian, lots of white space'. It opens a design thread and makes the FIRST version. It returns immediately with a job id; call check_generation to see the result, and do NOT describe the frame as made until that says so. The result is a preview in the thread — nothing is in the operator's frame list until save_frame is called with the generation they choose. To change a result, call refine_frame with the threadId that check_generation returns, rather than starting again. Every generation spends part of the account's free daily allowance, so do not call this speculatively, twice for the same request, or while another generation is still running.
Inputs: layout (required), prompt (required), shape. Returns: kind, note, what, error, +2 more
update_booth_draftChange a booth draft's settingsADestructiveIdempotentInspect
Change a booth draft without a redraw: its title, link name, welcome button text, colours, capture mode, language, which frames and filters it carries, its AI effect, and the page settings the dashboard editor offers (photo count, countdown, timeouts, GIF/recording, retake, checkout, payment, result). Use it after check_generation shows the draft and the operator asks for one of these; what it sets is applied when create_booth runs. It cannot change the welcome headline or subtext of an AI-designed welcome (those are painted into the image — use refine_booth with what='welcome' and headline), and prices or packages are set in the dashboard. Answers at once with the updated draft, applied (what landed) and rejected (what did not, and why) — relay a rejection as a sentence, never as success. It never touches a booth that already exists.
Inputs: draftId (required), slug, title, palette, +9 more. Returns: kind, note, what, draft, +7 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Ask your AI assistant about your class studio's own numbers. See upcoming classes and how full they are, find the classes that need promoting, and check fill rates, attendance, bookings, cancellations and revenue from classes, gift cards and private events. Read-only, and limited to the studio that connects.
Ask about your drone operation: projects, jobs, flights, pilots, maintenance and safety. Read-only.
Look up Momence members, class schedules, bookings and memberships, and handle front-desk actions.
Ask about your Shopify store's AI sales and support: revenue, shopper problems, and answer fixes.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceConnects an AI client to a Dreambooth Studio photobooth account so the operator can read photo sessions, gallery statistics, revenue, AI credits and wallet transactions, and manage booth projects. It also supports designing photo frames and filters and drafting new booths from prompts.MIT

ActivationKing MCPofficial
AlicenseNot gradedqualityBmaintenanceConnects AI assistants to a live-event photo booth account so they can look up events, guest sessions and credit balances, and read or manage companies, jobs and deals in an Ops Calendar. Supports syncing CRM deals and creating or updating jobs, with write actions flagged for confirmation.MIT- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to browse studio pose and outfit libraries, audit portraits against photography rules, perform zero-training biometric pose transfer, and query pricing and credits.51 npmMIT
- AlicenseCqualityBmaintenanceEnables studio owners to connect their own studio API key and query an assistant about availability, bookings, clients, packages, prices and business performance. Ships 150 API-backed tools—65 read/preview operations enabled by default and 85 opt-in mutations requiring confirmation and idempotency keys—plus guided prompts for monthly reviews, finding session times and preparing booking changes.65MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.