Skip to content

UGCfy AI MCP server

ai.ugcfy/ugcfy-mcpugcfy.aistreamable-httpv0.1.0Scanned

Break down any TikTok or Reels ad and rewrite it for your product. Hooks, scripts, CPM. No key.

5 tools: 5 change things.

Tools: 0 delete, 0 irreversible, 5 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 5
  • Can send data out · 0
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

5 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 UGCfy AI MCP server can do

The UGCfy AI MCP server is published by ugcfy.ai, a domain the MCP Registry verified. It has 5 tools. It can create or change data (5 tools: breakdown_ad, rewrite_ad_for_product, generate_hooks, write_ugc_script and 1 more), but cannot delete data. None of its tools only reads.

5 tools bring in text other people can write (breakdown_ad, rewrite_ad_for_product, generate_hooks and 2 more).

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.

Last scanned Nov 11, 2026, version 0.1.0.

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.

5 tools

Changes things 5Claude Code: ask
  • breakdown_adReverse-engineer a competitor TikTok or Instagram Reels ad: hook type and why it works, the segment-by-segment structure, selling points, call to action, and 2-3 copywriting moves …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.
    • 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.
    Description, as the server wrote it
    Reverse-engineer a competitor TikTok or Instagram Reels ad: hook type and why it works, the segment-by-segment structure, selling points, call to action, and 2-3 copywriting moves worth reusing. Pass a public video link, or paste the ad text if you already have it. Returns a breakdown_id you can hand to rewrite_ad_for_product.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • estimate_ad_costGive any two of budget (USD), impressions, and CPM, and get the third.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.
    • 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.
    Description, as the server wrote it
    Give any two of budget (USD), impressions, and CPM, and get the third. Free and unlimited.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • generate_hooksWrite 8 scroll-stopping opening lines for a UGC-style video ad, each labelled with its hook type (problem, curiosity, social proof, POV, before-after, negativity) and the psycholog…Reads text others write1 finding

    Why it is in this group

    • The name "generate_hooks" 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_hooks" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Write 8 scroll-stopping opening lines for a UGC-style video ad, each labelled with its hook type (problem, curiosity, social proof, POV, before-after, negativity) and the psychology behind it.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • rewrite_ad_for_productTake a reference ad (a breakdown_id from breakdown_ad, a video link, or pasted ad text) and write 1-3 scene-by-scene UGC script variants for a different product that keep the same …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.
    • 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.
    Description, as the server wrote it
    Take a reference ad (a breakdown_id from breakdown_ad, a video link, or pasted ad text) and write 1-3 scene-by-scene UGC script variants for a different product that keep the same hook type and structure without copying the competitor. Returns an open_url that loads the scripts into UGCfy AI, where the user can render them as videos with AI actors.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • openWorldHint: true
  • write_ugc_scriptAnalyze a product (link or description) and write 4 complete 20-30 second UGC video ad scripts with different angles, scene by scene, plus the product profile used (benefits, proof…Reads text others write1 finding

    Why it is in this group

    • The name "write_ugc_script" says "write": 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 "write_ugc_script" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Analyze a product (link or description) and write 4 complete 20-30 second UGC video ad scripts with different angles, scene by scene, plus the product profile used (benefits, proof points, objections). Use this when there is no reference ad to copy. Returns an open_url that loads the scripts into UGCfy AI to render as videos.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: 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 write5
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, 18:28 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
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 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://ugcfy.ai/api/mcp: tools/list returned 5 tools to an anonymous client, including breakdown_ad (write), rewrite_ad_for_product (write), generate_hooks (write), write_ugc_script (write), estimate_ad_cost (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

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

    Matched text

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

    What this check looks for
  • The server marks "write_ugc_script" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

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

    What this check looks for

History

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

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http ugcfy https://ugcfy.ai/api/mcp
claude mcp add --transport http ugcfy https://ugcfy.ai/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": [],
    "ask": [
      "mcp__ugcfy__breakdown_ad",
      "mcp__ugcfy__rewrite_ad_for_product",
      "mcp__ugcfy__generate_hooks",
      "mcp__ugcfy__write_ugc_script",
      "mcp__ugcfy__estimate_ad_cost"
    ],
    "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 ugcfy. Review it before you use it.

Capability tags behind 5 rules
  • mcp__ugcfy__breakdown_ad untrusted-input
  • mcp__ugcfy__rewrite_ad_for_product untrusted-input
  • mcp__ugcfy__generate_hooks untrusted-input
  • mcp__ugcfy__write_ugc_script untrusted-input
  • mcp__ugcfy__estimate_ad_cost 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/ai.ugcfy/ugcfy-mcp/verify?hash=f4d839894091c465ef1ea3c8b44dfd60acd82565b238dcf8067549f8fe7f7d3d" | jq -e '.changed == false'

Pinned hash f4d839894091, from Nov 11, 2026, 23:18 UTC.

Watch

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

https://radar.anlyon.com/servers/ai.ugcfy/ugcfy-mcp/changes.xml

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

Badge

Anlyon Radar badge for ai.ugcfy/ugcfy-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.ugcfy/ugcfy-mcp.svg)](https://radar.anlyon.com/servers/ai.ugcfy/ugcfy-mcp)

Source: MCP Registry. Synced Oct 21, 2026, 17:43 UTC.

UGCfy AI MCP server: questions and answers

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

Is the UGCfy AI MCP server safe?

No scan can promise that. What its definitions show: 5 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 UGCfy AI MCP server delete data?

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

Can the UGCfy AI 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 UGCfy AI MCP server have?

5 tools: 5 write. breakdown_ad, rewrite_ad_for_product, generate_hooks, write_ugc_script and estimate_ad_cost.

Does the UGCfy AI MCP server need sign-in or OAuth?

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

Does the UGCfy AI MCP server send data to outside services?

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

Has the UGCfy AI MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.