Skip to main content
Glama

Publish file from URL

publish_file

Publish a file fetched from a public http(s) URL, not a local path (max 5 MiB, video 20 MiB); HTML and Markdown files become pages. Returns the share link, the owner token and manageUrl (private: its holder can edit or delete). Owner tokens and management links never go into published content.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "publish_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
ttlDaysNoDays to keep it: up to 30 days without an account, up to 90 with a free profile (an ownerToken held in the profile). Omitted: the default. The result states the expiry.
filenameNoName instead of the URL's; its extension decides page or file
passwordNo
namespaceNo`public` for anything meant to be found or shared: listed in the gallery and sitemap, indexed by Google, Bing and AI search; unsuitable for secrets or personal data. Omit (default): private, a generated priv-* namespace, unlisted; the link still opens it. A custom name: 1-32 of a-z, 0-9, hyphen.
ownerTokenNoOwner token of an earlier create

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • removedInput schema / $schema
      Removed value: -"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / properties / deliveryMode
      Removed value: -{
      -  "description": "Optional delivery choice for a fresh publication, independent of password/namespace. Fresh sites and HTML-format pages outside public (including the default unlisted namespace) always use subdomain; an explicit path there still publishes, on subdomain, with a delivery notice. Everything else in any namespace (Markdown, code/text, files, JSON, KV, public HTML) defaults to path (Promotion); public HTML may automatically choose subdomain for browser features. When creation returns an existing publication, it keeps its actual mode and URL.",
      -  "enum": [
      -    "path",
      -    "subdomain"
      -  ],
      -  "type": "string"
      -}
    • changedInput schema / properties / filename / description
      Previous value: -"Custom filename (optional); replaces the URL's name, so its extension decides whether the file becomes a page"New value: +"Name instead of the URL's; its extension decides page or file"
    • changedInput schema / properties / namespace / description
      Previous value: -"Send namespace=public for anything meant to be found or shared (docs, guides, demos, portfolios, reports, landing pages): listed in the public gallery and sitemap, so Google, Bing and AI search index it and people discover it. Public pages are served on the brewpage.app domain itself, for the strongest search reach; code that needs its own origin (cookies, storage) gets its own subdomain automatically. Anyone can find and read a public page, so it is unsuitable for secrets, tokens or personal data. Omit (default): private, a generated priv-* namespace; unlisted, not indexed; the link still opens it. Lowercase only: 1-32 of a-z, 0-9, hyphen."New value: +"`public` for anything meant to be found or shared: listed in the gallery and sitemap, indexed by Google, Bing and AI search; unsuitable for secrets or personal data. Omit (default): private, a generated priv-* namespace, unlisted; the link still opens it. A custom name: 1-32 of a-z, 0-9, hyphen."
    • changedInput schema / properties / ownerToken / description
      Previous value: -"Optional; the ownerToken from your first create keeps publications under one owner. Default: env BREWPAGE_OWNER_TOKEN (local server only), else a new token per create."New value: +"Owner token of an earlier create"
    • addedInput schema / properties / password
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / ttlDays
      Added value: +{
      +  "description": "Days to keep it: up to 30 days without an account, up to 90 with a free profile (an ownerToken held in the profile). Omitted: the default. The result states the expiry.",
      +  "exclusiveMinimum": 0,
      +  "type": "number"
      +}
    • removedInput schema / properties / url / description
      Removed value: -"URL of the file to upload"
    • removedInput schema / properties / url / format
      Removed value: -"uri"
  2. Changed1 schema field changed
    • changedInput schema / properties / filename / description
      Previous value: -"Custom filename (optional)"New value: +"Custom filename (optional); replaces the URL's name, so its extension decides whether the file becomes a page"
  3. Changed1 schema field changed
    • changedInput schema / properties / namespace / description
      Previous value: -"namespace=public: listed in the public gallery and the sitemap, so Google, Bing and AI search can find and index it and people can discover it. Suits anything meant to be found or shared: docs, guides, demos, portfolios, reports, landing pages. Public pages are served right on the brewpage.app domain, which gives them the strongest reach in search; a page whose code needs its own origin (cookies, storage) gets its own subdomain automatically. Anyone can find and read a public page, so it is unsuitable for secrets, tokens or personal data. Omit (default): private. Unlisted and not indexed; anyone who has the link can still open it. Lowercase only: 1-32 of a-z, 0-9, hyphen."New value: +"Send namespace=public for anything meant to be found or shared (docs, guides, demos, portfolios, reports, landing pages): listed in the public gallery and sitemap, so Google, Bing and AI search index it and people discover it. Public pages are served on the brewpage.app domain itself, for the strongest search reach; code that needs its own origin (cookies, storage) gets its own subdomain automatically. Anyone can find and read a public page, so it is unsuitable for secrets, tokens or personal data. Omit (default): private, a generated priv-* namespace; unlisted, not indexed; the link still opens it. Lowercase only: 1-32 of a-z, 0-9, hyphen."
  4. Changed1 schema field changed
    • changedInput schema / properties / ownerToken / description
      Previous value: -"Optional. Default: env BREWPAGE_OWNER_TOKEN (local server only), else a new token per create."New value: +"Optional; the ownerToken from your first create keeps publications under one owner. Default: env BREWPAGE_OWNER_TOKEN (local server only), else a new token per create."
  5. Changed1 schema field changed
    • changedInput schema / properties / ownerToken / description
      Previous value: -"Optional. Default: BREWPAGE_OWNER_TOKEN, else a new token per create."New value: +"Optional. Default: env BREWPAGE_OWNER_TOKEN (local server only), else a new token per create."
  6. Changed2 schema fields changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / additionalProperties
      Removed value: -false
  7. Changed1 schema field changed
    • changedInput schema / properties / namespace / description
      Previous value: -"namespace=public: listed in the public gallery and the sitemap, so Google, Bing and AI search can find and index it and people can discover it. Use it for anything meant to be found or shared: docs, guides, demos, portfolios, reports, landing pages. Public pages are served right on the brewpage.app domain, which gives them the strongest reach in search; a page whose code needs its own origin (cookies, storage) gets its own subdomain automatically. Anyone can find and read a public page: never put secrets, tokens or personal data there. Omit (default): private. Unlisted and not indexed; anyone who has the link can still open it. Lowercase only: 1-32 of a-z, 0-9, hyphen."New value: +"namespace=public: listed in the public gallery and the sitemap, so Google, Bing and AI search can find and index it and people can discover it. Suits anything meant to be found or shared: docs, guides, demos, portfolios, reports, landing pages. Public pages are served right on the brewpage.app domain, which gives them the strongest reach in search; a page whose code needs its own origin (cookies, storage) gets its own subdomain automatically. Anyone can find and read a public page, so it is unsuitable for secrets, tokens or personal data. Omit (default): private. Unlisted and not indexed; anyone who has the link can still open it. Lowercase only: 1-32 of a-z, 0-9, hyphen."
  8. First observed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare write/non-destructive; the description adds real operational context — 5 MiB (20 MiB video) caps, the page-vs-file conversion rule, and what private owner tokens/manageUrl grant (edit or delete). The security warning about never embedding owner tokens in published content is genuinely useful. It stops short of covering overwrite/collision behavior or password/access semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and source constraint, then limits, then return values, then the token-safety caveat. Dense but every clause carries new information and none of it repeats the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly carries the return contract (share link, owner token, manageUrl and their meaning). For a 6-parameter mutation tool it is nearly complete, with the only gap being the unexplained password parameter and overwrite behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, so most parameters already carry their own documentation, including the important namespace privacy distinction and ttlDays account tiers. The description adds nothing parameter-specific and leaves the undocumented 'password' parameter unexplained in either place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Publish a file fetched from a public http(s) URL') and immediately scopes the source ('not a local path'), which separates it from content-based siblings like publish_html or publish_json. It also declares the downstream effect: HTML and Markdown become pages.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a hard input constraint (public http(s) URL, not a local path) and size limits, which implicitly narrows when the tool applies. However, it never explicitly names an alternative or says 'use publish_html when X instead', so the agent must infer the routing from sibling names alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.