Skip to content

urlhub

by urlhub.cloud · remote · no sign-in to list tools · v1.1.0 · published by cloud.urlhub

Many links as one short link with a QR code; read urlhub sets and preview what links are about.

Changes · 2

4 tools: 2 change things and 2 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http urlhub https://urlhub.cloud/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "featured_sets" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "featured_sets" says "set": a word for a change.

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 2Claude Code: ask
  • make_setMakes a urlhub set from links: a short link that opens a page with every link's picture, title and description, and its QR code as PNG and SVG files.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "make_set" says "set": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.urls): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Makes a urlhub set from links: a short link that opens a page with every link's picture, title and description, and its QR code as PNG and SVG files. Good when several links should travel together: sent to someone, opened later on a phone, or printed as one QR code on a poster or a slide (gift ideas, products to compare, a reading list, a trip plan, links for a class). With a title (and a description) it publishes the set as a page with that heading, for a set to send round or print; without one it makes a short link. Both are public to anyone who has the link. The same links always give the same link; to change a set, call make_set again. A short link nobody opens for 90 days goes away, a page after a year; long_link, when the list is short enough, holds every link in the address itself and never goes away.

    Annotations the server declares

    • title: Make a set of links
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 2Claude Code: allow, ask for 2 outbound
  • read_setReads a urlhub link someone gives you (a short link /c/…, a published page /l/…, a featured set /s/…, or an address with ?urls=) and returns its links with their titles and descrip…Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "read_set" says "read": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe description's first sentence says "read" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Reads a urlhub link someone gives you (a short link /c/…, a published page /l/…, a featured set /s/…, or an address with ?urls=) and returns its links with their titles and descriptions as Markdown.

    Annotations the server declares

    • title: Read a urlhub set
    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write3
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out3
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 14:25 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://urlhub.cloud/mcp: tools/list returned 4 tools to an anonymous client, including make_set (write), featured_sets (write)

    What this check looks for

Install

Pinned to version 1.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http urlhub https://urlhub.cloud/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__urlhub__make_set",
      "mcp__urlhub__read_set",
      "mcp__urlhub__preview_links",
      "mcp__urlhub__featured_sets"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as urlhub. Review it before you use it.

Capability tags behind 3 rules
  • mcp__urlhub__make_set untrusted-input, outbound
  • mcp__urlhub__read_set untrusted-input, outbound
  • mcp__urlhub__preview_links untrusted-input, outbound