Skip to content

b59.link MCP server

link.b59/b59-linkb59.linkstreamable-httpv1.2.0Scanned

Short links, QR codes and page-view trackers for AI agents, with click stats and email-code sign-up.

7 tools: 5 change things and 2 only read.

Tools: 0 delete, 0 irreversible, 5 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 3
  • Can send data out · 3
  • No findings

Sign-in required, no OAuth metadata. Remote posture

Anlyon alternative

5 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the b59.link MCP server can do

The b59.link MCP server is published by b59.link, a domain the MCP Registry verified. It has 7 tools. It can create or change data (5 tools: auth, shorten_url, generate_qr, create_tracker and 1 more), but cannot delete data. 2 tools only read.

3 tools bring in text other people can write (auth, get_stats_url and lookup_url); 3 tools can send data out of your system (shorten_url, generate_qr and lookup_url).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Oct 24, 2026, version 1.2.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Changes things 5Claude Code: ask
  • authSign in to b59.link to raise the rate limit from 2 to 300 requests/minute and own what you create.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Sign in to b59.link to raise the rate limit from 2 to 300 requests/minute and own what you create. Pass api_key to get a session key straight away. Or pass email to have a 6-digit code emailed, then call again with email and otp to get a session key (new emails are signed up and also get their api_key). Send the session key as the HTTP header 'Authorization: Bearer <session_key>'.

    Annotations the server declares

    • title: Sign in to b59.link
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • create_trackerCreate a free page-view tracker for a website.No findings

    Why it is in this group

    • The name "create_tracker" says "create": a word for a change.
    Description, as the server wrote it
    Create a free page-view tracker for a website. Returns the tag image URL and ready-to-paste snippets for the site's pages, plus the stats URL where views, visitors, pages and referrers are shown. When signed in, the tracker belongs to the account; otherwise keep the manage_token to claim it later.

    Annotations the server declares

    • title: Create a page-view tracker
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • generate_qrGenerate a trackable QR code for a URL.Can send data outNo findings

    Why it is in this group

    • The name "generate_qr" says "generate": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Generate a trackable QR code for a URL. Creates a b59.link short URL at the same time so scans are counted. Returns the short URL, a stats URL, and the QR code as a base64-encoded PNG.

    Annotations the server declares

    • title: Make a tracked QR code
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • make_qr_imageMake a QR code image for any text (URL, Wi-Fi string, phone, email, plain text) without creating a short link.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Make a QR code image for any text (URL, Wi-Fi string, phone, email, plain text) without creating a short link. Supports colors, size and SVG. Returns the image plus a permanent image URL that can be embedded with <img src>. Use generate_qr instead when scans should be counted.

    Annotations the server declares

    • title: Make a QR code image
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • shorten_urlShorten a long URL and get a memorable b59.link short URL.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Shorten a long URL and get a memorable b59.link short URL. Optionally specify a custom slug. Returns the short URL and a stats URL.

    Annotations the server declares

    • title: Shorten a URL
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 2Show 2 read-only tools
  • get_stats_urlGet the stats page URL for anything b59.link tracks: a slug or short URL, the destination URL of a short link or QR code, a tracker id or tag URL, or any page URL / domain that has…Reads text others writeNo findings

    Why it is in this group

    • The name "get_stats_url" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "get_stats_url" says "get" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Get the stats page URL for anything b59.link tracks: a slug or short URL, the destination URL of a short link or QR code, a tracker id or tag URL, or any page URL / domain that has a tracker tag. Stats themselves are viewed on b59.link; this returns where.

    Annotations the server declares

    • title: Find a stats page
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • lookup_urlCheck whether a URL already has a b59.link short URL.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "lookup_url" says "lookup": a word for reading.

    What it can reach

    • untrusted-inputThe name "lookup_url" says "lookup" and "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "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
    Check whether a URL already has a b59.link short URL. Handles variations: http/https, www prefix, trailing slash. Returns the existing short URL and QR code if found.

    Annotations the server declares

    • title: Look up an existing short link
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

Sign-in required, no OAuth metadata

Looked at Nov 15, 2026, 13:23 UTC, unchanged since Nov 8, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
525
tools/list served without credentials
no
Tools that change things, listed without credentials
0
Protocol version
not observed
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed

The probe stopped: initialize answered HTTP 525.

Posture changes

  1. Nov 8, 2026
    • HTTP status of an anonymous initialize: 200 to 525
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 6 to 0
    • Protocol version: 2025-06-18 to none
    • RFC 9728 protected resource metadata: https://b59.link/.well-known/oauth-protected-resource/api/mcp to none
    • Authorization servers: https://b59.link to none
    • Dynamic client registration: yes to not observed
    • Client ID metadata documents: no to not observed
  2. Oct 31, 2026
    • Tools that change things, listed without credentials: 5 to 6
    • RFC 9728 protected resource metadata: none to https://b59.link/.well-known/oauth-protected-resource/api/mcp
    • Authorization servers: none to https://b59.link
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 525; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 6 -> 0 (and 5 more).View diff
    • HTTP status of an anonymous initialize: 200 to 525
    • tools/list served without credentials: yes to no
    • Tools that change things, listed without credentials: 6 to 0
    • Protocol version: 2025-06-18 to none
    • RFC 9728 protected resource metadata: https://b59.link/.well-known/oauth-protected-resource/api/mcp to none
    • Authorization servers: https://b59.link to none
    • Dynamic client registration: yes to not observed
    • Client ID metadata documents: no to not observed
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 5 -> 6; RFC 9728 protected resource metadata: none -> https://b59.link/.well-known/oauth-protected-resource/api/mcp; Authorization servers: none -> https://b59.li…View diff
    • Tools that change things, listed without credentials: 5 to 6
    • RFC 9728 protected resource metadata: none to https://b59.link/.well-known/oauth-protected-resource/api/mcp
    • Authorization servers: none to https://b59.link
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to no

Install

Pinned to version 1.2.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http b59-link https://b59.link/api/mcp
claude mcp add --transport http b59-link https://b59.link/api/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": [
      "mcp__b59-link__get_stats_url"
    ],
    "ask": [
      "mcp__b59-link__auth",
      "mcp__b59-link__shorten_url",
      "mcp__b59-link__generate_qr",
      "mcp__b59-link__create_tracker",
      "mcp__b59-link__lookup_url",
      "mcp__b59-link__make_qr_image"
    ],
    "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 b59-link. Review it before you use it.

Capability tags behind 5 rules
  • mcp__b59-link__auth untrusted-input
  • mcp__b59-link__shorten_url outbound
  • mcp__b59-link__generate_qr outbound
  • mcp__b59-link__get_stats_url untrusted-input
  • mcp__b59-link__lookup_url untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/link.b59/b59-link/verify?hash=1fce5c0dbfa57f1f79da779df60b37db76594136613dd147443a16d02d6b11b8" | jq -e '.changed == false'

Pinned hash 1fce5c0dbfa5, from Oct 24, 2026, 09:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/link.b59/b59-link/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for link.b59/b59-link
[![Anlyon Radar](https://radar.anlyon.com/badge/link.b59/b59-link.svg)](https://radar.anlyon.com/servers/link.b59/b59-link)

Source: MCP Registry. Synced Oct 24, 2026, 10:18 UTC.

b59.link MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the b59.link MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the b59.link MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the b59.link MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the b59.link MCP server have?

7 tools: 5 write, 2 read. auth, shorten_url, generate_qr, create_tracker, make_qr_image, get_stats_url and lookup_url.

Does the b59.link MCP server need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the b59.link MCP server send data to outside services?

3 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): shorten_url, generate_qr and lookup_url.

Has the b59.link MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Oct 24, 2026.