Skip to content

AdCreator AI: Ad Creative Maker MCP server

com.adcreator-ai/generate-ad-headlinesadcreator-ai.comstreamable-httpv1.1.1Scanned

Turn a product photo into a finished ad image, or get up to 10 ad headlines. Free, no signup.

2 tools: 2 change things.

Tools: 0 delete, 0 irreversible, 2 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 0
  • 1 finding

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 AdCreator AI: Ad Creative Maker MCP server can do

The AdCreator AI: Ad Creative Maker MCP server is published by adcreator-ai.com, a domain the MCP Registry verified. It has 2 tools. It can create or change data (2 tools: make_ad_creative and generate_ad_headlines), but cannot delete data. None of its tools only reads.

2 tools bring in text other people can write (make_ad_creative and generate_ad_headlines).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 15, 2026, version 1.1.1.

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.

2 tools

Changes things 2Claude Code: ask
  • generate_ad_headlinesGenerate up to 10 ad headlines for an e-commerce / Shopify product.Reads text others write1 finding

    Why it is in this group

    • The name "generate_ad_headlines" says "generate": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "generate_ad_headlines" says "generate": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Generate up to 10 ad headlines for an e-commerce / Shopify product. Provide the product (name + short description); optionally an audience and the platform (Facebook, Instagram, Google, TikTok). Returns up to 10 distinct headlines (claims the description does not make are removed, so some calls return fewer), each labelled with the persuasion technique used. Read-only and free, no signup. If generation fails, the tool returns an error and no headlines.

    Annotations the server declares

    • title: Generate ad headlines for a product
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • make_ad_creativeTurn a product photo into a finished 1080x1080 social ad image (photo + headline + call to action) with matching ad copy, using AdCreator AI.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
    Turn a product photo into a finished 1080x1080 social ad image (photo + headline + call to action) with matching ad copy, using AdCreator AI. Provide the product (name + short description) and photo_url, a public https link to a JPEG, PNG or WebP photo (max 5 MB). Optionally a sale occasion (black-friday or cyber-monday) and the merchant's own offer (e.g. "25% off"), which is shown exactly as given; the offer is used only with an occasion. Returns a watermarked preview image URL plus headline, body and CTA. The photo is placed into a fixed ad layout; it is not generated or edited by an AI image model. Free, no signup; limited to 3 per client per day. If generation fails, the tool returns an error and no image.

    Annotations the server declares

    • title: Make an ad creative
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • 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 or outbound.

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 out0
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 20, 2026, 18:33 UTC, unchanged since Oct 29, 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://adcreator-ai.com/mcp-ads: tools/list returned 2 tools to an anonymous client, including make_ad_creative (write), generate_ad_headlines (write)

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 1 to 2

Findings

Matches of fixed checks, with the text they matched.

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

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "generate_ad_headlines" says "generate": a word for a change.

    What this check looks for

History

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

  1. Tools1 changed.~1 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 2.View diff
    • Tools that change things, listed without credentials: 1 to 2
  3. Tools1 added, 2 removed, 1 changed.+1 added−2 removed~1 changedView diff

Install

Pinned to version 1.1.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http generate-ad-headlines https://adcreator-ai.com/mcp-ads
claude mcp add --transport http generate-ad-headlines https://adcreator-ai.com/mcp-ads

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__generate-ad-headlines__make_ad_creative",
      "mcp__generate-ad-headlines__generate_ad_headlines"
    ],
    "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 generate-ad-headlines. Review it before you use it.

Capability tags behind 2 rules
  • mcp__generate-ad-headlines__make_ad_creative untrusted-input
  • mcp__generate-ad-headlines__generate_ad_headlines 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/com.adcreator-ai/generate-ad-headlines/verify?hash=d2153f09b77a41b0c9954881813b64a3b8dc37b176745b283bfa5f03f3e71526" | jq -e '.changed == false'

Pinned hash d2153f09b77a, from Nov 15, 2026, 16:18 UTC.

Watch

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

https://radar.anlyon.com/servers/com.adcreator-ai/generate-ad-headlines/changes.xml

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

Badge

Anlyon Radar badge for com.adcreator-ai/generate-ad-headlines
[![Anlyon Radar](https://radar.anlyon.com/badge/com.adcreator-ai/generate-ad-headlines.svg)](https://radar.anlyon.com/servers/com.adcreator-ai/generate-ad-headlines)

Source: MCP Registry. Synced Nov 15, 2026, 16:17 UTC.

AdCreator AI: Ad Creative Maker MCP server: questions and answers

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

Is the AdCreator AI: Ad Creative Maker MCP server safe?

No scan can promise that. What its definitions show: 2 tools, 2 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the AdCreator AI: Ad Creative Maker MCP server delete data?

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

Can the AdCreator AI: Ad Creative Maker 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 AdCreator AI: Ad Creative Maker MCP server have?

2 tools: 2 write. make_ad_creative and generate_ad_headlines.

Does the AdCreator AI: Ad Creative Maker MCP server need sign-in or OAuth?

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

Does the AdCreator AI: Ad Creative Maker MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the AdCreator AI: Ad Creative Maker MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.