此 MCP 可以做什么
Analyzes competitor Apple App Store advertising and supports creation of UGC avatars, video ad clips, subtitles, and assembled promotional videos.
功能
工具
17
工具
assemble_status
Check an assemble_video job by its job_id. Returns the status (processing, done, or error). When done, returns the final MP4 url, the aspect, clip count, total duration, and the booked cost in EUR. When it errored, returns the reason. Only jobs on your own account are visible.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'description': 'The job_id returned by assemble_video'}}, 'additionalProperties': False}
assemble_video
Stitch rendered scene clips into one ad-ready MP4 with burned-in subtitles and crossfades. Pass 1 to 6 clips in order, each with its mp4 url, its duration in seconds (3 to 12), and an optional subtitle line to burn over that clip. Every clip is scaled and padded to the chosen aspect (9:16 default 1080x1920, 1:1 1080x1080, or 16:9 1920x1080). Optional intro and outro title cards: pass intro/outro as { text, duration_s? } to bookend the ad with a centred title card (1 to 5 seconds, default 2) that crossfades into the video; cards do not count toward the 6-clip limit. Assembly is our compute, so it carries a small flat fee (about 0.12 EUR), booked only when the file is produced, against your trust cap. Runs in the background over up to a couple of minutes and returns a job_id: poll assemble_status with it to get the finished MP4 url. Feed it the clips from clips_status (map each to url, duration_s, subtitle). Paid plans only.
可访问外部资源
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['clips'], 'properties': {'clips': {'type': 'array', 'items': {'type': 'object', 'required': ['url', 'duration_s'], 'properties': {'url': {'type': 'string', 'description': 'Public mp4 URL of the rendered clip (http(s))'}, 'subtitle': {'type': 'string', 'maxLength': 120, 'description': 'Line to burn as a subtitle over this clip (the spoken line). Omit for none.'}, 'duration_s': {'type': 'number', 'description': 'Clip length in seconds (3 to 12)'}}, 'additionalProperties': False}, 'description': '1 to 6 clips in playback order'}, 'intro': {'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 120, 'description': 'Title text for the intro card'}, 'duration_s': {'type': 'number', 'description': 'Card length in seconds (1 to 5, default 2)'}}, 'description': 'Optional intro title card shown before the clips.', 'additionalProperties': False}, 'outro': {'type': 'object', 'required': ['text'], 'properties': {'text': {'type': 'string', 'maxLength': 120, 'description': 'Title text for the outro card'}, 'duration_s': {'type': 'number', 'description': 'Card length in seconds (1 to 5, default 2)'}}, 'description': 'Optional outro title card shown after the clips (e.g. a call to action).', 'additionalProperties': False}, 'aspect': {'enum': ['9:16', '1:1', '16:9'], 'type': 'string', 'default': '9:16', 'description': 'Output aspect ratio: 9:16 (default, 1080x1920), 1:1 (1080x1080), or 16:9 (1920x1080).'}}, 'additionalProperties': False}
clips_status
Check a generate_clips render job by its job_id. Returns the status (processing, done, or error). When done, returns the finished clip URLs, the model used, and the booked cost in EUR. When it errored, returns the reason. Only jobs on your own account are visible.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['job_id'], 'properties': {'job_id': {'type': 'string', 'description': 'The job_id returned by generate_clips with confirm=true'}}, 'additionalProperties': False}
generate_avatar
Generate a UGC persona: your agent passes a persona brief (physical look plus vibe of one invented creator), and we return stills of that invented person plus an avatar_id. The persona brief anchors the same character in generate_clips takes, and the stills are the customer's reference artifact for the creative. Ask for up to 3; the default model returns a single strong base still, imagen and flux return the full set. Metered per generation; the price is shown in the response. Paid plans only.
可访问外部资源
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['persona_brief'], 'properties': {'count': {'type': 'integer', 'default': 3, 'maximum': 3, 'minimum': 2, 'description': 'How many stills to request (2 to 3). The default model returns 1 regardless; imagen and flux honor this.'}, 'model': {'enum': ['bytedance/seedream-4.0', 'google/imagen-4.0-generate-001', 'bfl/flux-pro-1.1'], 'type': 'string', 'default': 'bytedance/seedream-4.0', 'description': 'Image model. Default seedream-4.0 (lowest cost).'}, 'persona_brief': {'type': 'string', 'minLength': 10, 'description': 'Physical description plus vibe of the invented UGC creator. One person (age, look, styling, setting, energy).'}}, 'additionalProperties': False}
generate_clips
Render UGC video scenes as ad-ready clips, metered per second of video (the estimate shows the exact price before anything renders). Pass 3 to 6 scenes (5 to 8 seconds each, one action per scene, spoken lines at most 20 words; empty spoken_line for silent characters). Consecutive scenes pack into single TAKES of up to 15 seconds, one generation each. HOW CHARACTER IDENTITY WORKS, read carefully: all characters are described in TEXT (avatar_id resolves to its persona brief; or write the persona field yourself, covering one character or a whole ensemble). The video model rejects every image that contains a person, so no photo can anchor a face. Text keeps a character IDENTICAL only WITHIN a take; ACROSS takes it preserves the look and styling but the exact face can drift, and neither avatar_id nor persona prevents that. Structure your script so scenes where the same character must be recognizably identical sit adjacent and fit one take (15s or less); treat cross-take appearances as different shots of a matching character, and review the result. reference_image_urls (up to 9 https images) keeps real products or props on-model in every take; these images must contain no people. Without confirm, it validates the contract and returns the per-scene price estimate in EUR, and makes nothing. With confirm=true it starts the metered render and returns a job_id: rendering runs in the background over a few minutes, so poll clips_status with that id to get per-scene clip URLs plus the uncut takes. Paid plans only.
可访问外部资源
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['scenes'], 'properties': {'model': {'enum': ['bytedance/seedance-2.0', 'bytedance/seedance-2.0-fast'], 'type': 'string', 'default': 'bytedance/seedance-2.0', 'description': 'seedance-2.0 (default, highest quality) or seedance-2.0-fast (same generation, faster and cheaper).'}, 'aspect': {'enum': ['9:16', '1:1', '16:9'], 'type': 'string', 'default': '9:16', 'description': 'Output aspect ratio'}, 'scenes': {'type': 'array', 'items': {'type': 'object', 'required': ['duration_s', 'setting', 'avatar_action', 'spoken_line'], 'properties': {'camera': {'type': 'string', 'description': 'Camera framing'}, 'energy': {'type': 'string', 'description': 'Delivery energy'}, 'setting': {'type': 'string', 'description': 'Where the scene happens'}, 'duration_s': {'type': 'number', 'description': 'Scene length in seconds (5 to 8)'}, 'spoken_line': {'type': 'string', 'description': 'Spoken line, at most 20 words. Empty string for a silent scene.'}, 'avatar_action': {'type': 'string', 'description': 'One gross action (hold, tap, point). No chained actions.'}}, 'additionalProperties': False}, 'description': '3 to 6 scenes in order. Adjacent scenes sharing a character land in the same take when their combined length allows it.'}, 'confirm': {'type': 'boolean', 'default': False, 'description': 'Set true to start the metered render. Returns a job_id to poll with clips_status.'}, 'persona': {'type': 'string', 'maxLength': 600, 'description': 'Alternative to avatar_id: describe the recurring character or the full ensemble (several characters) in words. Same limits: identity holds within a take, not across takes. Ignored when avatar_id is present.'}, 'avatar_id': {'type': 'string', 'description': 'Avatar id from generate_avatar (starts with av_). Its persona brief describes the recurring character in text; identity holds within a take only, not across takes.'}, 'reference_image_urls': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 9, 'description': 'Up to 9 https image URLs of products or props to keep on-model in every take. No people in these images.'}}, 'additionalProperties': False}
get_ad_details
Get full details and locale/creative variations for one specific ad (use adId from get_competitor_ads). Shows every language variant, creative asset URLs, and icon variations. Useful to see how a competitor localizes a winning ad.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['adId'], 'properties': {'adId': {'type': 'string'}, 'datePreset': {'enum': ['LAST_90_DAYS', 'LAST_180_DAYS', 'LAST_YEAR'], 'type': 'string', 'default': 'LAST_YEAR'}}, 'additionalProperties': False}
get_competitor_ads
Get all Apple App Store ads a competitor has run (EU storefronts, up to 1 year back), with creative copy, placements, formats, and an inferred winner analysis: ads sorted by how long they've been running (longevity = the advertiser keeps paying = likely converting). Source: official Apple Ad Repository (DSA transparency data).
只读
可访问外部资源
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['id'], 'properties': {'id': {'type': 'number', 'description': 'appId or developerId from search_app_advertiser'}, 'type': {'enum': ['APP', 'DEVELOPER'], 'type': 'string', 'default': 'APP'}, 'countries': {'type': 'array', 'items': {'type': 'string', 'maxLength': 2, 'minLength': 2}, 'description': 'EU country codes to filter (default: all 25). Available: AT,BE,BG,HR,CY,CZ,DK,EE,FI,FR,DE,GR,HU,IE,IT,LV,LU,NL,PL,PT,RO,SK,SI,ES,SE'}, 'datePreset': {'enum': ['LAST_90_DAYS', 'LAST_180_DAYS', 'LAST_YEAR'], 'type': 'string', 'default': 'LAST_YEAR'}}, 'additionalProperties': False}
get_playbook
Get a Recao GTM playbook: the go-to-market moves a solo app founder's agent runs, wired to the competitor data tools. Start with 'the-roadmap' (diagnoses the founder's stage and its binding constraint, then routes you to the right playbook). Call with no slug to list all playbooks.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'slug': {'type': 'string'}}, 'additionalProperties': False}
memory_index
List this account's company memory, one line per entry (name + description), newest first. Traverse index-first: scan this, then memory_recall(name) for full bodies. Memory accrues automatically from your competitor scans (exhaust) and from your own memory_note writes.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
memory_note
Write (or update) a memory entry on this account: decisions, campaign outcomes, learnings. Use a short kebab-case name and a one-line description (that's the index line); details go in body. Your future sessions and Recao's weekly reports read this.
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['name', 'description', 'body'], 'properties': {'body': {'type': 'string', 'maxLength': 20000, 'description': 'Full content (markdown fine)'}, 'name': {'type': 'string', 'description': "Short kebab-case slug, e.g. 'campaign-tiktok-hooks-june'"}, 'description': {'type': 'string', 'maxLength': 300, 'description': 'One-line summary for the index'}}, 'additionalProperties': False}
memory_recall
Read one memory entry's full body by name (get names from memory_index).
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['name'], 'properties': {'name': {'type': 'string', 'description': 'Memory name (kebab-case slug from memory_index)'}}, 'additionalProperties': False}
roadmap_status
Where the founder's agent starts its go-to-market work: diagnose which stage of the Recao Roadmap this account is in (S0 pre-launch to S4 scale), the binding constraint, and the playbook to run. Reads your scans and memory. Sharpen it: write a memory_note named 'company-stage' with your MRR band and funnel numbers, and this tool will use it.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
search_app_advertiser
Search the Apple Ad Repository for apps or developers advertising on the EU App Store. Returns ids to use with get_competitor_ads. Start here with your competitor's app name.
只读
可访问外部资源
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['name'], 'properties': {'name': {'type': 'string', 'minLength': 2, 'description': 'App or developer name to search for'}, 'types': {'enum': ['APP', 'DEVELOPER'], 'type': 'string'}}, 'additionalProperties': False}
sign_up
Request a free Recao account for your human. This does NOT create an active account: it registers a PENDING one and emails your human an activation link; nothing works and no terms are accepted until they click it (the human accepts the terms at activation, not you). The API key in the response stays inert until then. Consent stays with the human, so calling this is a request, not a decision made for them: in an interactive session their approval of this tool call is the go-ahead; if you run autonomously, surface this step to your human instead of calling it. After activation, reconnect with header `Authorization: Bearer <key>`.
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['email'], 'properties': {'email': {'type': 'string', 'description': "The account owner's email (the human founder's)"}, 'app_name': {'type': 'string', 'maxLength': 120, 'description': "The user's own app (App Store name), so reports and memory attach to it"}}, 'additionalProperties': False}
upgrade
Get the checkout link to upgrade this account to a paid plan (Indie â¬29/mo: 10 competitors + weekly auto-reports; Pro â¬79/mo: 25 competitors, new channels first, full API). Payment happens in the browser. Hand the link to the human.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['plan'], 'properties': {'plan': {'enum': ['indie', 'pro'], 'type': 'string'}}, 'additionalProperties': False}
usage
Show this account's metered generation spend this period and its billing position: the usage cap, what has accrued toward it, and whether generation is waiting on a payment. Use it to report costs back to your human.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
whoami
Show the authenticated account (plan, email, verification state), or confirm you're anonymous.
只读
幂等
输入模式
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
历史
近期工具变更
已添加
whoami
2026年9月17日 07:58
已添加
usage
2026年9月17日 07:58
已添加
assemble_status
2026年9月17日 07:58
已添加
assemble_video
2026年9月17日 07:58
已添加
clips_status
2026年9月17日 07:58
已添加
generate_clips
2026年9月17日 07:58
已添加
generate_avatar
2026年9月17日 07:58
已添加
roadmap_status
2026年9月17日 07:58
已添加
memory_note
2026年9月17日 07:58
已添加
memory_recall
2026年9月17日 07:58
已添加
memory_index
2026年9月17日 07:58
已添加
upgrade
2026年9月17日 07:58
已添加
sign_up
2026年9月17日 07:58
已添加
get_playbook
2026年9月17日 07:58
已添加
get_ad_details
2026年9月17日 07:58
已添加
get_competitor_ads
2026年9月17日 07:58
已添加
search_app_advertiser
2026年9月17日 07:58
发现
类似的 MCP 服务器
Hermoso
io.github.hermoso-ai/hermoso
Supports ad research, competitor analysis, video and static ad creation, campaign policy checks, content publishing, and performa…
Heista
co.heista/api
Analyzes video advertising, builds brand intelligence profiles, researches markets, and generates advertising scripts and creativ…
Spook SEO
com.tryspook/spook
Provides SEO analysis, keyword and content generation, AEO checks, ad copy tools and automated article generation and publishing.
VarynForge
com.varynforge/server
Supports SEO research and content planning through niche analysis, competitor and keyword research, opportunity discovery, and wr…
AfterLaunch: the agentic growth marketing engine
io.afterlaunch/agentic-growth-marketing
Runs growth-marketing workflows covering SEO, AI-search visibility, competitor analysis, content planning, distribution channels,…
RoboWrite
ai.robowrite/mcp
Supports brand setup, content briefs, AI-generated drafts, editorial review, quality checks, and publishing workflows.
ai-content-drop
com.aicontentdrop/ai-content-drop
Generates AI images, videos, UGC clips, avatars, and finished ads, while organizing creative assets and campaign boards.
Newswire Com
io.github.pipeworx-io/newswire-com
Searches and retrieves recent press releases from Newswire.com's public newsroom feed.