L1NK MCP server
website.l1nk/linksl1nk.websitestreamable-httpv1.0.0Scanned
Short links with QR, custom domains and bot-free click analytics. Create, edit, delete, analyze.
7 tools: 1 can delete or cancel things, 4 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 2
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the L1NK MCP server can do
The L1NK MCP server is published by l1nk.website, a domain the MCP Registry verified. It has 7 tools. It can delete or cancel things (1 tool: delete_link) and create or change data (4 tools: create_link, get_link, update_link and get_analytics). 2 tools only read.
1 tool brings in text other people can write (get_analytics); 2 tools can send data out of your system (create_link and update_link).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 1.0.0.
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
Deletes or cancels 1Claude Code: deny
delete_linkDelete a link permanently.No findings
Why it is in this group
- The name "delete_link" says "delete": a word for removing or ending something.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete a link permanently. Anyone opening it afterwards gets "not found". Confirm with the user first.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
Changes things 4Claude Code: ask
create_linkCreate a short link that redirects to a URL.Can send data outNo findings
Why it is in this group
- The name "create_link" says "create": 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 Create a short link that redirects to a URL. Returns shortUrl, which is what you share.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
get_analyticsClick analytics by people (bots reported apart): totals, daily series, countries, devices, browsers, referrers and top links.Reads text others write1 finding
Why it is in this group
- The name "get_analytics" says "get": a word for reading.
- The description's first verb is "click": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe description's first sentence says "click" and "browser": it reads web pages, which anyone can write.
Findings
- Warn
The server marks "get_analytics" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "get_analytics" says "get": a word for reading.
Description, as the server wrote it Click analytics by people (bots reported apart): totals, daily series, countries, devices, browsers, referrers and top links. On Pro (and the trial) also aiTraffic (visits from AI assistants such as ChatGPT or Perplexity, with their share and breakdown), cities (top 10 with their country) and QR scans; on Free those fields are null. For the whole account, or for one link with code. The plan caps how far back you can look (Free 30 days, Pro 365).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_linkDetails of one link: destination, destination rules (reglas) if any, clicks by people, bots apart (link previews and crawlers, not counted in clicks), creation and expiry dates, la…1 finding
Why it is in this group
- The name "get_link" says "get": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "get_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "get_link" says "get": a word for reading.
Description, as the server wrote it Details of one link: destination, destination rules (reglas) if any, clicks by people, bots apart (link previews and crawlers, not counted in clicks), creation and expiry dates, last click and recent click history. For countries, devices and referrers use get_analytics with the same code.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
update_linkChange where a link points, set a new expiry (Pro) or remove its expiry, or set destination rules (Pro): rotate clicks among several URLs (e.g.Can send data outNo findings
Why it is in this group
- The name "update_link" says "update": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
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 Change where a link points, set a new expiry (Pro) or remove its expiry, or set destination rules (Pro): rotate clicks among several URLs (e.g. a WhatsApp rotator between salespeople) or send by country or device. Also (Pro) an activation date, a click limit, and what visitors see when the link is not available. The short code stays the same.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 2Show 2 read-only tools
compare_tagsCompare the links that carry some tags (e.g.No findings
Why it is in this group
- The name "compare_tags" says "compare": a word for reading.
Description, as the server wrote it Compare the links that carry some tags (e.g. one QR per table, shop window or flyer): for each link, people, QR scans, bots apart and its top countries and devices, over the same period so the rows add up to the total. Without tags it only returns the tags the account uses (etiquetasDisponibles), to choose from. Pro plan (also during the 14-day trial).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_linksList the active (not expired) links of the account with their click counts and tags.No findings
Why it is in this group
- The name "list_links" says "list": a word for reading.
Description, as the server wrote it List the active (not expired) links of the account with their click counts and tags. Optionally only the links that carry any of the given tags.
Annotations the server declares
- readOnlyHint: 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 write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- 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 Nov 20, 2026, 19:20 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
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://l1nk.website/.well-known/oauth-protected-resource/api/mcp
- Authorization servers
- https://zlubrsnidqrbmobgsriw.supabase.co/auth/v1
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (1 destructive, 4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://l1nk.website/api/mcp: tools/list returned 7 tools to an anonymous client, including delete_link (destructive), create_link (write), get_link (write), update_link (write), get_analytics (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnget_link
The server marks "get_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "get_link" says "get": a word for reading.
- Warnget_analytics
The server marks "get_analytics" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":false}; The name "get_analytics" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added, 5 changed.+1 added~5 changedView diff
- Added:compare_tagsOnly reads
- Changed:create_linkChanges thingsinputSchema
- Changed:get_analyticsChanges thingsdescriptioninputSchema
- Changed:get_linkChanges thingsdescription
- Changed:list_linksOnly readsdescriptioninputSchema
- Changed:update_linkChanges thingsdescriptioninputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http links https://l1nk.website/api/mcp --header 'Authorization: <your-authorization>'claude mcp add --transport http links https://l1nk.website/api/mcp --header 'Authorization: <your-authorization>'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.
{
"permissions": {
"allow": [
"mcp__links__list_links",
"mcp__links__compare_tags"
],
"ask": [
"mcp__links__create_link",
"mcp__links__get_link",
"mcp__links__update_link",
"mcp__links__get_analytics"
],
"deny": [
"mcp__links__delete_link"
]
}
}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 links. Review it before you use it.
Capability tags behind 3 rules
- mcp__links__create_link outbound
- mcp__links__update_link outbound
- mcp__links__get_analytics untrusted-input
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/website.l1nk/links/verify?hash=cba279778870213a8376b43188a7072596ba100343c6b761a58b9aa45c275147" | jq -e '.changed == false'Pinned hash cba279778870, from Nov 19, 2026, 12:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/website.l1nk/links/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/website.l1nk/links)Source: MCP Registry. Synced Oct 21, 2026, 18:55 UTC.
L1NK MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the L1NK MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 2 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 L1NK MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: delete_link.
Can the L1NK 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 L1NK MCP server have?
- 7 tools: 1 destructive, 4 write, 2 read. delete_link, create_link, get_link, update_link, get_analytics, list_links and compare_tags.
Does the L1NK MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the L1NK MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_link and update_link.
Has the L1NK MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 5, 2026. Every change is on this page and in its Atom feed.