mcp server
CreativeScope — Mobile Game Ad Creative Intelligence
Mobile-game ad creative intelligence across SDK ad networks: search, rankings, AI hook analysis.
Description as published by the maintainer. Source
- version 1.0.0
- active
- retrieval
active — Most recent push to the repository was 2026-07-27. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
12 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
find_similar_creatives(limit, query, creative_id)- Find visually similar creatives using the stored vector of an existing creative. For a concept without an ID, query selects an explainable seed from available creative metadata and then uses the same vector-neighbor search. For an English concept, send the original English terms only. The service resolves Chinese source-label equivalents internally before selecting the seed. Returns creative records ordered from most to least visually similar; low-similarity and near-duplicate results are excluded, and raw similarity scores are not exposed. If request_echo.seed_basis identifies a proxy seed, clearly disclose that limitation instead of presenting the results as an exact concept match. Example: 'Show variants of the toilet run viral creative concept.'
generate_weekly_creative_brief(genre, limit, format, country, platform, date_range)- Generate a compact creative brief from recent high-signal mobile game ads. Use this for weekly inspiration, hook mining, competitor creative planning, and UA brainstorming. Creative tag fields are normalized to English in the result. Example: 'Create this week's puzzle-game creative brief for Facebook.'
get_advertiser_profile(advertiser_id)- Get an advertiser or game profile, including recent ad activity, creative volume, target countries, and platforms. Creative tag fields are normalized to English in the result. Example: 'Which markets and platforms is this game scaling on?' Required: advertiser_id.
get_creative_detail(creative_id)- Get one creative's delivery metadata and English creative insights, including opening hook signals, scene descriptions, and creative patterns when available. Example: 'Why does this winning creative work?' Required: creative_id.
get_creative_rankings(type, genre, limit, period)- Get global or genre-level rising creative rankings by day, week, or month, or evergreen creative rankings from the monthly snapshot; platform and country filters are not supported. Evergreen data is monthly only; day/week requests are normalized to month and disclosed in request_echo. Use this to answer what's rising this week, what evergreen creatives keep working, or which hook patterns repeat in a genre. For platform- or country-filtered discovery, use search_creatives and do not describe those results as an official rising or evergreen ranking. Creative tag fields are normalized to English in the result. Example: 'Which SLG creatives are rising this month?' Required: type, period.
get_game_rank_markets(limit, store, date_to, game_id, date_from, rank_types)- List the countries, app-store categories, stores, and ranking types where a game appeared on a chart during a date range. Returns each observed dimension with best rank, latest rank, and ranked-day count. Ranking types are free, store-paid, and top-grossing. Only Google Play and iPhone App Store are exposed; iPad rankings are excluded. Date range defaults to the last 90 days and cannot exceed 365 days. Required: game_id.
get_game_rank_trend(mode, store, country, date_to, game_id, category, date_from, rank_types)- Get one mobile game's daily app-store ranking performance over a date range. Returns free, store-paid, and top-grossing ranking series with best/latest rank and the matched country, category, and store. Use mode=best to select the game's best daily rank across supported countries and categories, or mode=exact for one country/category/store combination. Supported stores are Google Play, iPhone App Store, and all (Google Play plus iPhone App Store). Date range defaults to the last 90 days and cannot exceed 365 days. Required: game_id.
get_reference_image_search_results(limit, job_id)- Get completed reference-image search results. If the job is still running, returns polling guidance. Example: 'Show the matches from my reference-image search.' Required: job_id.
get_reference_image_search_status(job_id)- Get the processing status of a reference-image search job. Example: 'Is my reference-image search finished yet?' Required: job_id.
search_advertisers(genre, limit, query, region, platform)- Search advertisers, game studios, or mobile games by name and optional genre, region, and platform filters. Use the returned advertiser_id with get_advertiser_profile. Example: 'Find the advertiser for Last War.' Required: query.
search_creatives(genre, limit, query, format, country, platform, date_range, orientation)- Search mobile game ad creatives by keyword or visual-description-like natural language. For an English request, send the original English concepts only. The service internally expands genre, hook, mood, art-style, and gameplay-mechanic concepts to Chinese source-label equivalents for retrieval; generated translations must not be inserted into the public request. Use this for finding UGC-style ads, winning creatives, opening hook examples, playable ads, and platform/country/genre slices. Results include the original creative asset as media_url when available. Creative tag fields are normalized to English in the result. Example: 'Find UGC-style match-3 video ads in the US.' Required: query.
submit_reference_image_search(genre, limit, format, country, platform, image_url)- Submit a reference-image similarity search as an asynchronous job. Use this when the user provides a directly downloadable public HTTPS image URL. The URL must resolve to image bytes without login or hotlink protection; HTML pages, local paths, and base64 are not supported. The embedding provider validates image format and size asynchronously and returns IMAGE_FETCH_FAILED, INVALID_IMAGE, or EMBEDDING_MODEL_ERROR when processing cannot continue. Genre aliases are normalized internally. If a normalized genre produces no candidates, the completed result explicitly marks a visual-only fallback instead of silently returning an empty set. Example: 'Find ads visually similar to this reference image.' Required: image_url.
Last successful function declaration observed on . Source: https://mcp.creativescope.ai/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://mcp.creativescope.ai/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 0 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-27 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.0.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-22 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-22 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 12 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | mcp.creativescope.ai | |
| mcp endpoint status | ok | The server listed 12 functions when asked. | as of probe | mcp.creativescope.ai |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json