Do I need to sign up or provide an API key?
No. Publishing works without an account. An optional free profile manages all your pages.
Brewpage MCP Server
@kochetkov-ma
基本情報
Brewpage MCP Server について
Publish HTML, Markdown, KV, JSON, and files to brewpage.app from AI assistants. 5 tools, stdio, no signup. Returns public short URL + owner token per artifact.
Brewpage MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"brewpage": {
"command": "npx",
"args": [
"-y",
"brewpage-mcp@1.14.4"
]
}
}
}Brewpage MCP Server のツール
20Publish HTML or Markdown content to BrewPage (repository default limit 5 MiB). Returns its primary share link and owner token. Supports password protection, custom TTL, optional filename, and an opt-in top toolbar (showTopBar). When deliveryMode is omitted for a `public` page, the server may publish it on its own subdomain if the page needs browser features a BrewPage link does not provide; the result then includes deliveryModeReason and a delivery notice. Markdown raw HTML is allowlisted: scripts, styles, event handlers, forms and embeds are removed. Returns manageUrl, a private management link (grants control; not for public sharing). Secrets allowed; likely ones are flagged in notices. Private namespace + password suit secrets.
Upload a file to BrewPage via URL. Repository defaults: 5 MiB for files/audio, 20 MiB for video. Returns its primary share link and owner token. Does not expose password or TTL inputs. Returns manageUrl, a private management link (grants control; not for public sharing). Secrets allowed; likely ones are flagged in notices. Private namespace + password suit secrets.
Change delivery mode for a NEW publication (not a site, not a non-public HTML-format page). Requires owner token; optional expectedVersion = current hostingVersion. Mismatches are reported, not rejected: a stale version still applies, and OLD links or forced subdomain modes stay unchanged; the result then carries a delivery notice. Content updates never change hosting.
Delete a BrewPage resource (HTML page, site, KV store, JSON document, or file) using the owner token.
Fetch stored rendered HTML or format-specific code/text by namespace and ID. This reads API content, not the owner-only original-source endpoint or browser viewer. Protected reads use the password header.
Get BrewPage platform-wide usage statistics including page count, file count, and storage usage. Counts use disjoint split: alive_public + alive_private + deleted == total. Optional `tz` shifts the 'today' boundary to the given IANA zone (default UTC).
Publish an HTML site to BrewPage. Single-page: `entryContent`. Multi-page: `files` (array of `{path, content}`). Optional `entry` overrides default `index.html`. Returns its primary share link and owner token. Default limits (current values: GET /api/limits): a request is at most 25 MB; a site at most 200 files, 5 MB per file and 20 MB in total; each path at most 380 characters. System files (.DS_Store, __MACOSX/ and similar) are skipped and never count; files with an unsupported extension or a too-long path are skipped and listed in notices. Entry: `entry`, else root index.html, else the shallowest HTML file. Errors: 400 = a site limit exceeded (the message names it), invalid path or no HTML file; 413 = request over 25 MB, too many files and form fields, or a file name/path too long; 422 = no servable file left. Returns manageUrl, a private management link (grants control; not for public sharing). Secrets allowed; likely ones are flagged in notices. Private namespace + password suit secrets.
Republish (full-replace) an existing multi-file BrewPage site in place at the SAME URL/ID. Requires owner token. The uploaded bundle becomes the complete new file set — files absent from it are removed, new files added, matching files overwritten. Single-page: `entryContent`. Multi-page: `files` (array of `{path, content}`). Optional `entry` overrides the default `index.html`. Republishing preserves existing expiry. Old publications (made before 5 October 2026) are read-only: 409 OLD_PUBLICATION_READ_ONLY with createUrl to publish anew. Default limits (current values: GET /api/limits): a request is at most 25 MB; a site at most 200 files, 5 MB per file and 20 MB in total; each path at most 380 characters. System files (.DS_Store, __MACOSX/ and similar) are skipped and never count; files with an unsupported extension or a too-long path are skipped and listed in notices. Entry: `entry`, else root index.html, else the shallowest HTML file. Errors: 400 = a site limit exceeded (the message names it), invalid path or no HTML file; 413 = request over 25 MB, too many files and form fields, or a file name/path too long; 422 = no servable file left.
Update an existing BrewPage HTML/Markdown page. Requires owner token. Returns the updated page metadata. The link and delivery mode never change on update; an advisory deliveryModeReason and delivery notice are included when the new content uses browser features that may not work fully on a BrewPage link. Old publications (made before 5 October 2026) are read-only: 409 OLD_PUBLICATION_READ_ONLY with createUrl to publish anew.
Publish a JSON document to BrewPage (repository default limit 1 MiB). Accepts a JSON object, array, or a JSON-encoded string containing any valid JSON, including scalars/null. Returns its primary share link and owner token. Returns manageUrl, a private management link (grants control; not for public sharing). Secrets allowed; likely ones are flagged in notices. Private namespace + password suit secrets.
Fetch a published BrewPage JSON document by namespace and ID.
Update an existing BrewPage JSON document. Requires owner token. Accepts a JSON object, array, or a JSON-encoded string. Old publications (made before 5 October 2026) are read-only: 409 OLD_PUBLICATION_READ_ONLY with createUrl to publish anew.
Publish a key/value entry to BrewPage. Creates a KV store; the entry is addressed by (namespace, id, key). Repository defaults: 1 MiB per value, 1,000 keys per store; the key name `hosting` is reserved. Returns its primary share link and owner token. Returns manageUrl, a private management link (grants control; not for public sharing). Secrets allowed; likely ones are flagged in notices. Private namespace + password suit secrets.
Set or update a key in an existing BrewPage KV store. Requires owner token. The key name `hosting` is reserved. Old publications (made before 5 October 2026) are read-only: 409 OLD_PUBLICATION_READ_ONLY with createUrl to publish anew.
Fetch a value from a BrewPage KV store by namespace, ID, and key.
Get the current BrewPage upload limits (GET /api/limits): request size, site file count, per-file and total size, ZIP expansion, path and name lengths, TTL default/maximum, allowed file extensions and skipped system files. Sizes are bytes. With BREWPAGE_OWNER_TOKEN set: also reach (token|profile) and ownerMaxTtlDays.
Search the BrewPage public gallery. Optional filters: text query, pagination, sort, and 'mine' (owner-scoped, requires owner token).
Hide or show a public publication in the gallery and sitemap. Link unchanged.
Add an owner token to your BrewPage profile (as publish). Needs an admin token of that profile.
Mint a new profile token with an admin token; the new token is shown once. Scope publish (default) or admin; expiry 30d, 90d, 1y or never.
概要
What is BrewPage MCP?
BrewPage MCP is a Model Context Protocol server for BrewPage, free instant hosting with no signup and no API key. Claude, ChatGPT, Cursor, Codex, Gemini CLI and any MCP client can publish HTML, Markdown, multi-file sites, JSON, key-value data and files, and get back an HTTPS link plus an owner token.
How to connect
- Remote (no install): add
https://brewpage.app/mcpas a remote MCP server (Streamable HTTP, no auth). - Local (stdio):
npx -y brewpage-mcp@1.14.4. OptionalBREWPAGE_URLoverrides the defaulthttps://brewpage.app.
Tools (20)
Publish: publish_html, publish_site, publish_file, publish_json, publish_kv. Update: update_html, republish_site, update_json, set_kv, update_hosting, set_visibility. Read: get_page, get_json, get_kv, get_limits, get_stats, search_gallery. Manage: delete_resource, bind_token, mint_token. Every tool carries a title and read-only/destructive hints.
Use cases
- An agent publishes its HTML or Markdown report and returns the link.
- CI posts a test or coverage report as a page.
- Share a generated prototype or small static site.
- Keep small JSON or key-value state between agent runs.
よくある質問
How do I update or delete content?
Each publish returns an owner token. Pass it to the update or `delete_resource` tools. Keep it: it is the key to that publication.
Limits and retention?
Pages and files up to 5 MB (video 20 MB), sites up to 20 MB. Links expire: 15 days by default for API and agent publications, 30 days for public editor pages, up to 30 days without a profile or 90 days with a free profile. An unlisted link is not private; use a password for anything sensitive. Call `get_limits` for current values. Docs: https://brewpage.app/api · llms.txt: https://brewpage.app/llms.txt · Source: https://github.com/kochetkov-ma/brewpage-openapi
「ファイルとストレージ」の他のコンテンツ
File Context Server
bsmi021A Model Context Protocol (MCP) server that provides file system context to Large Language Models (LLMs). This server enables LLMs to read, search, and analyze code files with advanced caching and real-time file watching capabilities.
37
MCP File System Server
MarcusJellinghausMCP Workspace Server: A secure Model Context Protocol server providing file, git, and GitHub tools for AI assistants within a sandboxed project directory.
49
Storacha MCP Storage Server
storachaStoracha MCP storage server - self-sovereign data for your AI applications.
13
mcp-v8: V8 JavaScript MCP Server
r33drichardsMCP server that exposes a V8 JavaScript runtime as a tool for AI agents like Claude and Cursor. Supports persistent heap snapshots via S3 or local filesystem, and is ready for integration with modern AI development environments.
47
HTMLvault
AI tools (Claude, ChatGPT, Gemini, Grok, etc.) generate HTML constantly, from reports to landing pages to prototypes, but there's no easy way to share it or know if anyone looked. HTMLvault turns any HTML into a clean, t
コメント