MCP App Store
by KeenEthics
Ava Studio icon

Ava Studio MCP Server for ChatGPT

By Hologram Labs

Overview

Research short-form video references, manage brand media, draft campaign concepts, generate images, video and audio, and edit or export projects in Ava Studio. Sign in with Ava to choose permissions and a monthly credit budget. Actions use existing account credits and return usage information.

How to connect

  1. ChatGPT: Open the Ava Studio listing in the ChatGPT app directory and choose Connect. ChatGPT listing Ava Studio exposes 95 tools here.

Tools

audio_generate

ChatGPT
Generate a voiceover from a script in a voice from voices_list, music from a prompt, or a sound effect from a prompt (or matched to a video with mmaudio); it is saved to the user's Studio library, ready for timeline_add. Costs Studio's price for the model and settings (the same media credits as in Ava Studio): quote it with generation_estimate first. Returns a job_id; poll jobs_get for the audio.

ava_ask

ChatGPT
One turn with Ava, the campaign copilot of Studio's Ask Ava (shared with Studio): her reply plus her actions, for 40 credits per message plus the AI usage. Via the API she starts nothing that spends credits: she reads, discusses, approves and edits drafts (with this key's campaigns scopes); plans, drafting, production, research and settings come back failed, naming the tool to use (plan_run, concepts_draft_more, creative_produce, research_*, campaign_update). Returns a job_id; poll jobs_get.

brand_create

ChatGPT
Research a brand from its website, save a full brand profile (products, audience, tone, claims, customer insights) and analyze up to 12 of the images and videos it found so productions can use them. Costs 40 credits. Takes a minute or two: returns a job_id; poll jobs_get until succeeded, then the result is the Brand, whose media_readiness says what media is still missing.

brand_delete

ChatGPT
Permanently delete a brand profile, as Studio's Delete brand does (its campaigns and projects stay); ask the user first and pass confirm true, since it cannot be undone. If it was the primary brand another brand becomes primary; returns deleted_brand_id and primary_brand_id (null when no brand is left).

brand_export

ChatGPT
Export a brand profile as a portable brand.md (format md) or raw JSON (format json). Use it to save brand context into a repo or hand it to another tool.

brand_get

ChatGPT
Read a brand profile; pass sections to fetch only part of it (identity, audience, products, sources, visual, market). Use before drafting to check claims and audience (fix gaps with brand_update), and before producing to check the visual section's media_readiness: below good, videos get no B-roll and AI-generated product shots, so ask the user for real media (brand_media_upload_url, brand_media_add) or make clips with broll_create.

brand_list

ChatGPT
List the account's brands (id, name, url, primary flag). Use it to pick a brand_id for research and drafting; call brand_get for full details.

brand_media_add

ChatGPT
Add 1-10 images or videos to a brand (https links, brand_media_upload_url's media_url or brand_get urls; 30 max) and analyze each so Ava can use it; non-H.264 video, such as an iPhone's HEVC, is converted to an H.264 MP4 copy. Costs 2 credits per item imported and analyzed: failed lists items not added, analyzed false with analysis_error marks items added but not analyzed (add again to retry), neither charged. Returns a job_id; jobs_get then has the items and media_readiness.

brand_media_remove

ChatGPT
Remove 1-30 items from a brand's media by media_id (from brand_get), so Ava stops using them; the stored files are kept. Returns the ids removed, those not found and the brand's media_readiness.

brand_media_update

ChatGPT
Change one brand media item's label or description (when and how Ava should use it); a description set here wins over the machine analysis. Pass media_id from brand_get and label, description or both; returns the updated item and the brand's media_readiness.

brand_media_upload_url

ChatGPT
For clients that can PUT bytes, get a presigned link to upload one local image (JPEG, PNG or WebP, up to 10 MB) or video (MP4, MOV or WebM, up to 50 MB) for a brand: PUT the file bytes to upload_url with exactly the returned headers before expires_at (15 minutes). Then pass media_url to brand_media_add to add and analyze it; public links need no upload, pass them to brand_media_add directly. Videos that are not H.264 (such as HEVC/H.265 from an iPhone) are converted to H.264 MP4 when added.

brand_set_primary

ChatGPT
Make a brand the account's primary brand, the one Ava Studio opens by default and whoami marks is_primary. Returns primary_brand_id and the previous primary brand.

brand_update

ChatGPT
Edit a brand profile and get the updated Brand back. patch holds only the fields to change (arrays replace the whole list). Use claim_status / insight_status to approve or exclude existing claims and insights.

broll_create

ChatGPT
Make one 5-second vertical B-roll clip from 1-4 of the brand's images (product photos, app screens or web pages, by media_id) with a Studio B-roll template; the clip joins the brand's media, analyzed. Costs the media credits Studio charges for it, about 75 (a key with a monthly limit needs room for them). Returns a job_id (a few minutes); poll jobs_get, the result is the new media_item and its project_id, and media_credits_charged what the media cost.

campaign_accounts_apply

ChatGPT
Rebuild an organic campaign's posting accounts from the account plan, after asking the user: planned accounts can be added, resized or removed; paused accounts and accounts marked is_yours in campaign_accounts_get are kept. weekly_posts asks for a different total, and dismiss: true keeps the accounts and hides the current update. It sets the campaign's weekly concept volume, so pause automation first.

campaign_create

ChatGPT
Create an organic or paid campaign with the actual app/product brief and objectives; first use campaign_list/get to reuse the user's selected campaign. Creation does not plan or generate: use plan_get/plan_run, concept_list, approval and creative_produce on this same campaign_id, not draft_briefs' separate container. Automation starts off; returns the Campaign and studio_url for optional settings changes.

campaign_evidence

ChatGPT
Read a saved campaign run's references, linked concepts and public counters; these measure reference posts, never results of generated creatives. Choose source_id for concepts_draft_more, and use plan_list for older weeks. No credits are charged and no new research is performed.

campaign_get

ChatGPT
Read one campaign: brief, objective, type, automation settings, featured brand media and a summary of its latest plan run. Call plan_run to research and draft concepts, or concept_list to see the ones already drafted.

campaign_list

ChatGPT
List the account's Ava Studio campaigns, newest first, optionally for one brand: name, type, automation and whether setup is complete. Use campaign_get for a campaign's settings and latest plan run, or campaign_create to start one.

campaign_results

ChatGPT
Read up to 12 of a campaign's best live post results that have views, from saved data: Ava's posts on managed accounts and posts on tracked accounts from the last 3 weeks, and creatives the user posted and linked; tracked posts only fill what is left. Each result has views; the 24-hour and 48-hour marks appear once they are read, and the account's baseline and the ratio against it (2 or more is a winner) once the account has enough earlier posts.

campaign_update

ChatGPT
Change a campaign's name, brief, objective or featured brand media, pause automation, or save its schedule and time zone while paused; send only changed fields to get the updated Campaign. Enabling or rescheduling active automation is refused because scheduled work runs outside API prices and key budgets; use plan_run for each run. Manage automation, formats, cast and media budgets in Studio.

captions_generate

ChatGPT
Add timed captions to a project from its voiceover, or from the audio element given, as Studio's auto captions do. Costs Studio's price for caption timing: 2 credits per started minute of audio, at least 2 (a 2-minute voiceover costs 4). Returns a job_id; poll jobs_get for the captions and media_credits_charged.

cast_suggest

ChatGPT
Suggest actors for a concept: up to 3 library actors that match its source performer (gender, age, style) and the user's own actors. Pass the chosen actor_id values to concept_versions_create.

concept_approve

ChatGPT
Approve 1-20 draft concepts into the campaign's production queue; if one fails, none are approved, and approving starts no production. Concepts that need an actor picked first come back in needs_cast with a Studio link while the rest are approved; produce approved ones with creative_produce.

concept_draft_get

ChatGPT
Read a campaign concept's editable draft, scripts and submitted versions with project ids; before_version pages older history. May initialize Studio's draft bookkeeping without starting production. For changes call concept_draft_update action:start_editing, then save with the returned draft_id/revision; submitted versions remain immutable.

concept_draft_update

ChatGPT
Edit campaign scripts, their order, carousel copy or storyboard direction using Studio's version workflow; saving generates no media and costs no credits. Read concept_draft_get, call action:start_editing, then action:save with returned draft_id/revision and patch, then action:submit to queue a version for separate approved production. Existing projects stay intact; slides_update/timeline_update edit existing on-screen text and layout.

concept_list

ChatGPT
List a campaign's concepts (the creative ideas Ava drafted), newest first, optionally for one plan run or status: hook, status, output kind and creative_id once approved. A concept_id is also a brief id, so draft_get shows its full script; then approve with concept_approve or reject with concept_reject.

concept_reject

ChatGPT
Reject a draft concept, with an optional reason Ava uses as feedback when she drafts later concepts. Only concepts with status draft can be rejected (anything else is invalid_input); returns the updated concept.

concept_versions_create

ChatGPT
Approve a draft concept as 1-4 versions, one per actor: an actor_id from cast_suggest, or "lookalike" for the closest library match. Produce each returned concept_id with creative_produce. Returns a job_id; poll jobs_get.

concepts_draft_from_source

ChatGPT
Draft one concept that remakes a source from source_add for the campaign's brand: format, script, preview frame and media_needs; one draft runs at a time per campaign, and a post with nobody on camera fails with invalid_input. Costs 10 credits, which Studio charges when the concept is saved (jobs_get reports them as media_credits_charged; a failed draft costs nothing). Returns a job_id; poll jobs_get, then call cast_suggest.

concepts_draft_more

ChatGPT
Draft 1-5 more concepts into the campaign's current plan run, reusing its research; call plan_run first if this period has no run yet. Costs 10 credits per concept drafted; it never produces media, so on a campaign whose mode is produce it fails with invalid_input. Returns a job_id; poll jobs_get, the result lists the new concepts.

creative_get

ChatGPT
Read one creative (an approved or produced concept): production status, output URLs, the post package (caption, hashtags, publish status) and its Studio project. To change it, edit the project with project_edit and get a new file with export_render.

creative_list

ChatGPT
List a campaign's creatives (approved and produced concepts), newest first, optionally for one plan run: status, output URLs and project ids. Call creative_get for one creative's post package, or creative_produce on approved concepts not produced yet.

creative_mark_posted

ChatGPT
Record that the user posted a creative on their own TikTok or Instagram account, with the post link, after they confirm it. Ava then reads that post at 24 hours, 48 hours and 7 days and counts it in the campaign's results, and the creative leaves the scheduling list. posted: false undoes it.

creative_produce

ChatGPT
Produce one concept into finished media (video, carousel or static image) like Studio's Generate button, which picks an actor if none is set. Costs 50 credits plus the media credits Studio charges (about its credit_range; a key's monthly limit needs room for both); no fee when already produced or producing (started false) or production fails. Takes minutes: returns a job_id; poll jobs_get for the Creative, or a failed job whose error names the reason and the creative for creative_get.

draft_briefs

ChatGPT
Write standalone video/carousel/static briefs only; complete videos use project_ask and campaign planning uses plan_run. Costs 10 credits per brief plus the AI usage (typically about 25 total); returns a job_id to poll with jobs_get. Always saves to the brand's 'From your agent' draft container, cannot target another campaign or supply creative_produce; use draft_get/spec/prompts/check/open to read or refine.

draft_check

ChatGPT
Score a brief 0-100 against winning videos in its niche, with strengths, risks and the most similar winners; the score is an AI judgment, not a calibrated prediction of performance. Costs 3 credits plus the AI usage, typically ≈ 4 credits in total. Use it to compare briefs before committing; revise weak ones with draft_iterate.

draft_clone

ChatGPT
Clone one short-form video (TikTok, Instagram Reel or YouTube Short URL) into ONE on-brand brief that keeps its format, beats, pacing, hook mechanic and caption style. Sources up to 2 minutes. Costs 10 credits plus the AI usage, typically ≈ 25 credits in total; returns a job_id: poll jobs_get, then use draft_spec, draft_prompts or draft_open on the brief, saved in the brand's "From your agent" campaign in Ava Studio.

draft_get

ChatGPT
Read one brief in full (script, storyboard, rationale, status). Use after draft_list or to re-check a brief after draft_iterate.

draft_iterate

ChatGPT
Revise a brief from plain-language feedback (a punchier hook, less salesy, a different CTA); only revises briefs created through the API. Costs 8 credits plus the AI usage, typically ≈ 15 credits in total. Returns a job_id; poll jobs_get, the result is the revised Brief.

draft_list

ChatGPT
List recent briefs, newest first, optionally for one brand or campaign. Use draft_get for full details.

draft_open

ChatGPT
Get the Ava Studio link where the brief can be reviewed, approved and produced. Share it with the user when they want to see or approve a draft.

draft_prompts

ChatGPT
Write per-shot generation prompts for a specific video or image model (seedance-2, veo-3.1, kling-3, sora-2, runway-gen4, nano-banana, gpt-image, generic). Carousel and static briefs get one image prompt per slide and need an image target (nano-banana, gpt-image or generic). This tool only writes prompts; to fulfill a generation request, quote generation_estimate then call video_generate or image_generate after approval and poll jobs_get for the media.

draft_spec

ChatGPT
Turn a brief into a shot list: per-shot role, duration, action, framing, camera, performer, speech, on-screen text and audio. Follow with draft_prompts for model-specific prompts, then video_generate or image_generate after the user approves the estimate.

export_render

ChatGPT
Render a Studio project to a downloadable MP4 or image file; watermark:auto (default) follows the owner's plan, watermark:required includes it, and watermark:none requires a paid owner. Costs 10 credits. Free when the project is unchanged since its last export with the same watermark setting; poll jobs_get for output_url.

generation_estimate

ChatGPT
Quote 1-20 generations at Studio's media credits for the model and settings (what the API charges too), plus the total; video bills on the clip's measured length, which can run a frame long (4 s may bill as 4.04 s). Work priced after the fact is quoted at its most: image_layerize at 17 layers of a large image (up to 1536×1536 pixels costs half), video_remove_background at the duration given (else 60 s). Tell the user the total first; a key with a monthly limit needs room for it.

image_generate

ChatGPT
Generate 1-4 images with any Studio image model from a prompt, optionally editing or steering with reference images; they are saved to the user's Studio library, and with save_to_brand_id to that brand's media. Costs Studio's price for the model and settings (the same media credits as in Ava Studio): quote it with generation_estimate first. Returns a job_id; poll jobs_get for the images' urls and library_asset_ids.

image_layerize

ChatGPT
Split an image into editable transparent layers (subject, text, background); the layers are saved to the user's Studio library. Costs Studio's price for the model and settings (the same media credits as in Ava Studio), per layer made (2-17): generation_estimate quotes all 17 at the large-image price, the most it can cost (a key with a monthly limit needs room for that); an image up to 1536×1536 pixels costs half. Returns a job_id; poll jobs_get for the layers.

image_reframe

ChatGPT
Reframe an image to another aspect ratio, extending the scene past its edges; the result is saved to the user's Studio library. Costs Studio's price for the model and settings (the same media credits as in Ava Studio): quote it with generation_estimate. Returns a job_id; poll jobs_get for the image.

jobs_get

ChatGPT
Check a job from any tool that returns a job_id; its kind is the tool's name. Poll every few seconds until status is succeeded or failed: result holds the tool's output (failed project_ask jobs can also retain partial results), credits_charged the API credits it cost and media_credits_charged the media credits its generation spent (while running: credits_held and media_credits_estimate).

launch_style_list

ChatGPT
List launch videos that went viral on X, labeled by industry, sector, audience and launch type and for remixing with a brand kit (format, remix path), with views, length and the original post. Use it for a launch, feature or fundraise video in a proven style. If the user named no reference, pick one and show it before building (poster_url, credit, post_url, why it fits), then read it with launch_style_get.

library_add

ChatGPT
Import 1-10 media files: ChatGPT attachments in files (Ava downloads them; no PUT), or public URLs/completed uploads in items. Links are copied into Ava's storage, uploads stay where they are, and other video codecs are converted to an H.264 MP4 copy. Poll jobs_get for library_asset_id and failed; use {library_asset_id} in video_generate, image_generate or project_ask.

library_list

ChatGPT
List the user's Studio media library, newest first, optionally by kind or origin (generated or uploaded): each asset's library_asset_id, url, kind and length. Pass {library_asset_id} to any media input, such as timeline_add's source or video_generate's start_image.

library_upload_url

ChatGPT
For clients that can PUT bytes, get a presigned link to upload one local image (JPEG, PNG or WebP, up to 50 MB), video (MP4 or MOV, up to 500 MB) or audio file (MP3, WAV or M4A, up to 9.2 MB): PUT the bytes to upload_url with exactly the returned headers before expires_at (15 minutes). Then pass media_url to library_add or a media input as {url}; an unused upload_url contains no file. For ChatGPT attachments use library_add files instead.

meta_connect

ChatGPT
Get the Ava Studio link where the user connects the brand's Meta ad account (Meta sign-in happens in their browser, not through the API). Show the connect_url and instructions to the user, then call meta_status once they are done.

meta_status

ChatGPT
Check whether a brand's Meta ad account is connected, which account, when it last synced and how many ads it has. Call before research_my_ads; if connected is false or needs_reconnect is true, call meta_connect.

meta_sync

ChatGPT
Pull the latest ads and results from the brand's connected Meta account (the same sync Ava Studio runs). Costs 10 credits, so run it only when last_synced_at is old; recent syncs are refused with a retry time. Returns a job_id; poll jobs_get, the result is the status after the sync.

models_list

ChatGPT
List the image, video and audio models Studio offers, optionally of one kind: modes, aspect ratios, durations, resolutions, qualities, reference limits and Studio's credit prices (the API charges the same). Pick a model here before image_generate, video_generate, audio_generate or scene_generate, then quote the cost with generation_estimate.

plan_get

ChatGPT
Read a campaign's plan run (the latest unless period_start is given): status, step labels, concept counts and ids, and Ava's research summary and strategy. Use it to follow a run started in Studio or by the schedule; when status is ready, call concept_list.

plan_list

ChatGPT
List saved campaign runs and their Monday-Sunday display weeks in the campaign timezone. Use week_start to browse a week and before/next_cursor for older runs; run ids remain exact dates, not week ids.

plan_run

ChatGPT
Use for campaign planning: research the selected campaign and draft its concepts, then concept_list, approval and creative_produce on the same campaign_id. Costs 200 credits, only when it starts a run; check plan_get first, since an existing current-period run returns started:false without a charge. Takes minutes and produces no media; poll jobs_get, and never substitute standalone draft_briefs for this planner.

project_ask

ChatGPT
Run Studio's content-planning agent for a complete original app/product video or a video/photo-carousel clone; start with project_create/list and pass brief/assets. Costs 10 credits plus AI tokens and Studio media; AI holds grow within balance/budget, media_credit_limit bounds estimated media (default 300). Plan with generate:false, media_credit_limit:0 (AI billed); after approval reuse the SAME project with generate:true, relay needs_input and poll jobs_get; campaign planning uses plan_run.

project_create

ChatGPT
Create a Studio project for a brand/campaign; next use project_ask for a complete original video or clone, keeping the same project_id through planning, approved generation and export_render. Linking campaign_id organizes the project but does not run campaign planning: use plan_run and creative_produce for that. For manual editing use scene_generate, timeline_add and captions_generate.

project_edit

ChatGPT
Apply one plain-language edit to a produced project's timeline: retime or trim scenes and b-roll, cut dead air, move captions onto their beat or off a face or the product, resize or move picture-in-picture and split-screen media. It cannot change words, add, remove or regenerate scenes, or touch music and voice. Costs 10 credits plus the AI usage; returns a job_id, poll jobs_get, then call export_render for the edited file.

project_from_template

ChatGPT
Make a project from a Studio template with your variables: only what depends on them changes (a scene generated from a variable you change is generated again, media variables swap in your file, text variables fill in); the rest stays as in the template (template_get: each scene's depends_on, and what is fixed). Costs Studio's price for the template: its 10-credit base fee plus each scene it generates at its model's price; template_get quotes it. Returns a job_id; poll jobs_get.

project_get

ChatGPT
Read a Studio project: scenes in timeline order (type, timing, status, caption, selected media and latest generation), every timeline element with its id, the captions and other on-screen text with their position and style, the script lines and the latest export; prompts stay hidden. Read it before project_edit, timeline_add or timeline_remove; call export_render for a fresh file.

project_history

ChatGPT
Read a project's saved user and assistant conversation, including reference attachments, when reconnecting or continuing work from another client. Newest messages first with next_cursor for older pages, excluding internal prompts and tool traces.

project_list

ChatGPT
List the account's Studio projects (editable videos and image sets), newest first, optionally for one campaign. Call project_get for a project's scenes and captions.

research_breakouts

ChatGPT
Find sampled videos above Ava's sampled creator view baseline for a niche or brand. Costs 1 credit per call. Explain the derived breakout denominator and cite linked posts with dated public counters and publication dates; engagement does not establish conversions and small samples need caveats.

research_formats

ChatGPT
Rank video formats in Ava's corpus; scores are internal heuristics with no calibrated success threshold. Costs 1 credit per call. Explain the pick with source links, public metrics, publication/measurement dates, sample limits and brand fit; carry it into the selected campaign/project brief, or draft_briefs.format for standalone written briefs only.

research_hooks

ChatGPT
Find opening hooks from sampled videos, grouped by pattern with source links. Costs 1 credit per call. Cite public metrics and dates, label hook scores as analysis estimates, and carry the evidence into the selected campaign/project brief; use draft_briefs only for standalone written briefs.

research_my_ads

ChatGPT
Read the user's Meta ad results with account medians and explanations; call meta_status first and use meta_connect if disconnected. Cite ads by name and carry the evidence into the selected campaign/project brief. Winning ad_ids can seed draft_briefs.my_ad_ids for standalone written briefs only.

research_similar

ChatGPT
Find videos with similar hooks or visual style using a video_id or text. Costs 2 credits per call. Similarity is relevance, not performance; cite platform links and dated public counters, describe brand fit and state missing evidence instead of treating internal scores as proof of success.

scene_generate

ChatGPT
Generate 1-4 variants of one scene of a project with any image or video model, into a scene from project_get or a new one after the last. Costs Studio's price for the model and settings (the same media credits as in Ava Studio), per variant: quote it with generation_estimate (count = variant_count). Returns a job_id; jobs_get gives the variants and, for a scene without media, where the first ready one went (placement); swap in another with scene_select_variant.

scene_select_variant

ChatGPT
Put one of a scene's generated variants on the timeline, as picking it in Studio does; returns the scene with its media. The generation and variant ids come from scene_generate's result.

slides_update

ChatGPT
Edit a carousel or static-image project's on-slide text, text styles, positions or slide order without generating images. Read project_get first: items use element ids, slide_order is the complete scene_id order, and expected_revision prevents stale saves. Call export_render for updated images/ZIP; baked-in text needs a separately approved targeted image edit.

source_add

ChatGPT
Add a TikTok post or direct video link as a remake source; without campaign_id it uses the brand's own Remakes campaign (made on first use) and never starts research or plan_run. Remakes need a person on camera: a post Ava already screened as hands-only, animated or product-only is refused here, otherwise at the draft. Pass source_id to concepts_draft_from_source.

template_get

ChatGPT
Read one Studio template: the variables to fill (text or media, required or with a default), each scene's variables and whether changing them generates it again, what stays fixed (music, voiceover, an actor without a variable), its preview and the quote for making a project from it (Studio's media credits). Pass the variables to project_from_template.

template_list

ChatGPT
List Studio's video templates, optionally for one use case or matching words in the title: title, use case, aspect ratio and preview. Read one with template_get for its variables and price, then make a project with project_from_template.

tiktok_accounts_list

ChatGPT
List the user's Managed Accounts (real US TikTok accounts our team warms and posts from) and orders, with status, final @handle once ready, niches, ready-by date, paid_through and posts_left. Ready accounts with a handle can take posts (tiktok_post_schedule).

tiktok_posts_list

ChatGPT
List posts scheduled on the user's Managed Accounts with day, window, caption and status (scheduled, posted with post_url and metrics, failed with failure_reason, cancelled).

timeline_add

ChatGPT
Add 1-20 items to a project's timeline in one change: video, image or audio from a link, brand media or the library, or text, each at a start time with an optional duration, track, position and style. Returns the new elements with their ids; check the result with project_get and render it with export_render.

timeline_remove

ChatGPT
Remove 1-50 elements from a project's timeline by element_id (from project_get or timeline_add) in one change; ids not on it come back in not_found.

timeline_update

ChatGPT
Change 1-20 elements of a project's timeline in one change: move, retime or trim them, set volume or mute, reposition a video, image or text, restyle text, or move a clip between the main and overlay tracks. A video's own sound moves and trims with it. Returns the changed elements with their style; element ids come from project_get or timeline_add.

tracked_account_add

ChatGPT
Track a public TikTok or Instagram account the user posts to themselves, by @handle or profile link. Ava reads its posts once a day and at 24 hours, 48 hours and 7 days after each post, from the plan's daily tracking allowance rather than credits. Private and missing accounts are refused.

tracked_account_remove

ChatGPT
Stop tracking an account in a campaign. Saved posts stay; no new reads.

tracked_accounts_list

ChatGPT
List the TikTok and Instagram accounts the user tracks in a campaign (accounts they post to themselves) with their recent posts and views at 24 hours, 48 hours and 7 days, from saved data. Ava uses these posts as topic evidence; it never drafts for or posts to them.

tracked_accounts_refresh

ChatGPT
Read the latest posts of a campaign's tracked accounts that are older than the plan's freshness, from the daily tracking allowance rather than credits. Returns at once with reading when reads continue in the background; call tracked_accounts_list after a minute.

video_generate

ChatGPT
Generate a video from a prompt and optional reference media, saved to the user's Studio library and optionally save_to_brand_id; Costs Studio's price for the model and settings (the same media credits as in Ava Studio): quote it with generation_estimate first. After the user approves the estimate, call this tool to start generation; prompts alone do not generate. Returns a job_id (minutes); poll jobs_get and share the video URL.

video_remove_background

ChatGPT
Cut the subject out of a video (a link, brand media or a library asset) onto a transparent background; the result is saved to the user's Studio library. Costs Studio's price for the model and settings (the same media credits as in Ava Studio), per second of video: quote it with generation_estimate. Returns a job_id; poll jobs_get for the video and its alpha mask.

video_upscale

ChatGPT
Upscale a video (a link, brand media or a library asset) with FlashVSR; the result is saved to the user's Studio library. Costs Studio's price for the model and settings (the same media credits as in Ava Studio): quote it with generation_estimate. Returns a job_id; poll jobs_get for the video.

voices_list

ChatGPT
List the voices Studio offers for voiceovers (name, gender, accent, description and a preview link); with query, also search ElevenLabs' community voices. Pass a voice_id to audio_generate.

whoami

ChatGPT
Check the API key and see the account: user id, credit balance and brands. Call this first in a session; if brands is empty, call brand_create next.

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/ava-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/ava-studio)