Skip to content

URL2Ad MCP server

app.url2ad/url2adurl2ad.appstreamable-httpv1.1.0Scanned

Turn a web page into a 15-second animated video ad: free preview from a URL and an e-mail.

3 tools: 2 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 2 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

2 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

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 URL2Ad MCP server can do

The URL2Ad MCP server is published by url2ad.app, a domain the MCP Registry verified. It has 3 tools. It can create or change data (2 tools: create_ad and request_change), but cannot delete data. 1 tool only reads.

2 tools bring in text other people can write (create_ad and request_change); 1 tool can send data out of your system (create_ad).

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

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 13, 2026, version 1.1.0.

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.

3 tools

Changes things 2Claude Code: ask
  • create_adStarts building a free watermarked 15-second video ad from a public web page, in the language of that page.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "create_ad" says "create": 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.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Starts building a free watermarked 15-second video ad from a public web page, in the language of that page. Use it when the user asks for a video ad for their site, product, app or store. The address must be the user's own, given by them in this conversation: never guess it or use someone else's. It receives the link by e-mail. Calling it again with the same page and address returns the same ad.

    Annotations the server declares

    • title: Create a video ad from a web page
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • request_changeRebuilds an existing ad with a change the user asked for, such as other wording, colors or images.Reads text others writeNo findings

    Why it is in this group

    • The name "request_change" says "request": 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.
    Description, as the server wrote it
    Rebuilds an existing ad with a change the user asked for, such as other wording, colors or images. It uses up one of the changes left, and one free change is included, so call it only when the user asked for this change, and pass their request as they said it. The new version takes a few minutes: follow it with get_ad_status.

    Annotations the server declares

    • title: Change a video ad
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • get_ad_statusReturns the state of an ad started with create_ad: building, preview_ready, paid, failed or unavailable, with its page link, the changes left and the reason for a failure.No findings

    Why it is in this group

    • The name "get_ad_status" says "get": a word for reading.
    Description, as the server wrote it
    Returns the state of an ad started with create_ad: building, preview_ready, paid, failed or unavailable, with its page link, the changes left and the reason for a failure. Use it when the user asks whether their ad is ready, or before saying that it is. To wait for an ad being built, pass wait_seconds and call again while the status is building.

    Annotations the server declares

    • title: Check where a video ad stands
    • 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 write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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.

Tools listed without sign-in

Looked at Nov 16, 2026, 14:21 UTC, unchanged since Nov 2, 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
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
  • 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://url2ad.app/mcp: tools/list returned 3 tools to an anonymous client, including create_ad (write), request_change (write)

    What this check looks for

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. Tools2 changed.~2 changedView diff

Install

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

claude mcp add --transport http url2ad https://url2ad.app/mcp
claude mcp add --transport http url2ad https://url2ad.app/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__url2ad__get_ad_status"
    ],
    "ask": [
      "mcp__url2ad__create_ad",
      "mcp__url2ad__request_change"
    ],
    "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 url2ad. Review it before you use it.

Capability tags behind 2 rules
  • mcp__url2ad__create_ad untrusted-input, outbound
  • mcp__url2ad__request_change 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/app.url2ad/url2ad/verify?hash=a4547e73df3c6c6632bdf1228571a0c65c45ae8db6e42c31a927e60650e5bc5b" | jq -e '.changed == false'

Pinned hash a4547e73df3c, from Nov 13, 2026, 22:17 UTC.

Watch

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

https://radar.anlyon.com/servers/app.url2ad/url2ad/changes.xml

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

Badge

Anlyon Radar badge for app.url2ad/url2ad
[![Anlyon Radar](https://radar.anlyon.com/badge/app.url2ad/url2ad.svg)](https://radar.anlyon.com/servers/app.url2ad/url2ad)

Source: MCP Registry. Synced Nov 1, 2026, 01:17 UTC.

URL2Ad MCP server: questions and answers

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

Is the URL2Ad MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 2 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 URL2Ad MCP server delete data?

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

Can the URL2Ad 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 URL2Ad MCP server have?

3 tools: 2 write, 1 read. create_ad, request_change and get_ad_status.

Does the URL2Ad MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the URL2Ad MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_ad.

Has the URL2Ad MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.