MCP 服务器

anew

page.anew/anew
设计与创意 开发者工具 公开且可连接 MCP 2026-07-28

此 MCP 可以做什么

Encodes self-contained HTML, CSS, and JavaScript pages into deterministic shareable URLs and can read them back.

anew_editor
anew
Open anew from the sidebar: the editor, fullscreen, on a new blank page. Takes no arguments.
只读
输入模式
{'type': 'object', 'required': [], 'properties': {}, 'additionalProperties': False}
anew_page
Page Editor
Open a page in the anew editor beside the chat, so the user can edit it by hand: pass an anew.page URL to open that page, or nothing for a new blank page. The editor reports the page it holds back to the chat after every edit. Call it only when the user asks to open the editor or to edit a page themselves; anew_write and anew_read do everything else.
只读
输入模式
{'type': 'object', 'required': [], 'properties': {'url': {'type': 'string', 'description': 'An anew.page URL or bare slug to open in the editor. Omit it, or leave it empty, for a new blank page.'}}, 'additionalProperties': False}
anew_read
Read a page (anew.page URL → its HTML source)
Pass an anew.page URL, get back the HTML document encoded in it, plus its canonical URL and byte size. (Two in-page tools share this name and take no arguments: the editor's reads the document open in the editor, and a rendered page's reads the page being viewed. This one takes a url and reads that page.) To revise an existing anew page, its URL is its source: read it, edit that HTML, write it again. The new URL is a separate page and the original keeps working. Read returns the author's exact bytes — no anew-injected tags, no proxied image srcs — so it re-encodes byte-for-byte. Never re-author from a rendered page, a scraped DOM, or a screenshot: each loses the author's markup, and none is faster than reading the slug. Decoding is local and exact, so any anew URL reads — the page needs no prior visit and no fetch.
只读
输入模式
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'minLength': 1, 'description': 'An anew.page URL, or a bare slug. Subdomain, cosmetic-prefix and #hash forms all resolve.'}, 'format': {'enum': ['text', 'resource'], 'type': 'string', 'default': 'text', 'description': 'How the document rides back. "text" (default) is one plain text block. "resource" is one embedded-resource block ({type:"resource"}, mimeType text/html) — the typed MCP form for callers that want the page tagged as HTML rather than loose text. Same bytes both ways.'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['url', 'bytes'], 'properties': {'url': {'type': 'string', 'format': 'uri', 'description': 'Canonical anew.page URL for this document.'}, 'bytes': {'type': 'integer', 'description': 'Encoded URL length in bytes.'}}, 'additionalProperties': False}
anew_write
Write a page (HTML → anew.page URL)
Publish a web page: encode one self-contained HTML document (or fragment, or plain text) into an anew.page URL and return that URL. Use it when the user asks for a page, a site or a link they can open and share. The page is carried in the URL itself — no account, and no copy of the page is kept — so anyone who has the URL can open it; each call also starts a screenshot of the page, cached publicly for link previews. Put markup and inline CSS in html and any JavaScript in javascript as plain source; the server inserts it before </body>. Inline the page's CSS, scripts and images so it renders on its own; a webfont may load from a CDN. Each encoding path is deterministic: the same input through the same path always produces the same URL. Different paths use different Brotli encoders, though, so the same HTML may mint different — equally valid — URLs; compare pages by their decoded HTML, never by slug. Limits: a page past 65000 URL bytes or 1048576 decoded bytes is refused with an error, and a URL over 4000 bytes works but may be cut short by apps it is shared through — the result then carries a warning. To revise an existing anew page, its URL is its source: read it, edit that HTML, write it again. The new URL is a separate page and the original keeps working. Read it with anew_read first, then call this with the edited HTML.
可访问外部资源
输入模式
{'type': 'object', 'required': ['html'], 'properties': {'html': {'type': 'string', 'minLength': 1, 'description': 'The page: HTML markup with inline CSS — a full document, a fragment, or plain text. Its JavaScript goes in javascript. Encoded into the returned URL.'}, 'javascript': {'type': 'string', 'minLength': 1, 'description': 'Optional client-side JavaScript for the page, as plain source without script tags. The server inserts it immediately before </body> (or at the end when there is no body).'}}, 'additionalProperties': False}
输出模式
{'type': 'object', 'required': ['url', 'bytes', 'decoded_bytes'], 'properties': {'url': {'type': 'string', 'format': 'uri', 'description': 'The anew.page URL of the page.'}, 'bytes': {'type': 'integer', 'description': 'Encoded URL length in bytes.'}, 'warning': {'type': 'string', 'description': 'Present when the URL is over 4000 bytes: the page works, and some apps cut a link that long short when it is shared.'}, 'decoded_bytes': {'type': 'integer', 'description': 'The submitted HTML in UTF-8 bytes.'}}, 'additionalProperties': False}
已添加
anew_editor
2026年10月3日 02:58
已添加
anew_page
2026年10月3日 02:58
已更改
anew_read
2026年10月3日 02:58
已更改
anew_write
2026年10月3日 02:58
已添加
anew_read
2026年9月17日 12:54
已添加
anew_write
2026年9月17日 12:54