For agents给 AI 用
The same label for an AI: an MCP server, an installable skill, llms.txt, a Markdown twin of every page and a JSON API. Public, read-only, no keys.同一个厂牌，给 AI 读：MCP 服务、可安装的技能包、llms.txt、每个页面的 Markdown 版本，以及 JSON 接口。公开、只读、不需要 key。
The MCP server
https://aidols.fans/mcp — Model Context Protocol over Streamable HTTP. No account, no key, no state.基于 Streamable HTTP 的 MCP。不需要账号、不需要 key、不保存状态。
Connect接入
Tools (9)工具（9 个）
list_artistsEvery artist on the label: slug, name, one-line thesis, medium, number of films, whether it is a labelled demo. Start here.
no parametersartist_canonWho an artist is, as data: the constants (what never changes), the identity text to paste into every prompt (long for close and medium shots, short for full-length and wide), every look with its wardrobe text, the voice, the never-list, credit and terms. Call this before making anything with an artist.
artistlist_filmsFilms on the label (or one artist's): logline, length, the production numbers (song, edit, stills, motion, time), frames, and the making-of documents.
artistbrowse_imagesPage through the images films were made from. scope: film (first frames in the finished cut), her (the artist is in it), all. Returns compact entries; get_image has the rest.
artist · film · scope · batch · look · framing · offset · limitsearch_imagesFull-text search over every image prompt, id, batch, look and set. All words must match.
query · artist · film · limitget_imageOne image: the exact prompt and params, size, framing, look, set, whether it is a plate in the film, the judge's or director's verdict, its siblings and URLs. id is artist/film.batch.job.n as returned by browse_images.
id · include_imageget_guideA wiki page as Markdown, optionally one section (by its heading). Topics: start, status, master, make, films, package, audition, ledger, money, agents, build.
topic · sectionget_recordA film's making-of document as Markdown, in pages: readme (the story, numbers, cost), prompts-stills, prompts-motion, song.
artist · film · doc · offset · max_charsbuild_promptCompose an image prompt for an artist from their canon: the framing, the identity text (long or short by distance, word for word), a look's wardrobe, your scene and light, the medium, and the safety tail. Paste the result into any image model.
artist · scene · framing · look · lightA first session第一次怎么用
list_artists → artist_canon("echo-vale") → search_images("rooftop night") → get_image(id, include_image=true) → build_prompt(…)
Resources and prompts资源与预设提示
castpad://artist/{slug}/canon·castpad://film/{artist}/{film}·castpad://record/{artist}/{film}/{doc}·castpad://wiki/{topic}castpad_still— Make one still of an artist that stays on canon.castpad_film— Plan a short music video for an artist the way the label's films are made.
The skill技能包
Inside: the skill, every artist's canon, the wiki, every film's record and a standard-library script that searches prompts and downloads images. Read it first:包里有：技能说明、每位艺人的设定、wiki、每支片的制作记录，以及一个只用 Python 标准库的脚本，可以搜提示词、下载图片。先读一下： SKILL.md
llms.txt and Markdown与 Markdown
- /llms.txt — the index索引
- /llms-full.txt — everything in one file全部内容一个文件
- Any page: add .md to the address — 任何页面：地址后加 .md —— /s/echo-vale.md, /wiki/start.md
JSON
/api/index.jsonthe site: artists, wiki, every endpoint
/api/films.jsonevery film on the label, with numbers and documents
/api/shows/{artist}/films.jsonone artist's films
/api/shows/{artist}/films/{film}one film with every image and its prompt
/api/shows/{artist}/images/{film.batch.job.n}one image
/api/shows/{artist}/master.jsonan artist's canon as data
/api/shows/{artist}/receipts?downloadan artist's full record, replayable
Every endpoint sends Access-Control-Allow-Origin: *. Keep agents polite: cache what you fetch, take the small images unless you need the large ones.所有接口都允许跨域。请客气一点：抓过的内容缓存起来，不需要大图时取小图。
End of reel.本卷完。