Is the AI Website Summarizer MCP server safe?

No scan can promise that. What its definitions show: 3 tools, 1 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 AI Website Summarizer MCP server delete data?

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

Can the AI Website Summarizer 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 AI Website Summarizer MCP server have?

3 tools: 1 write, 2 read. get_ai_prompt_links, get_widget_embed_code and get_integration_docs.

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

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

Does the AI Website Summarizer 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): get_ai_prompt_links.

Has the AI Website Summarizer MCP server changed its tools?

Not since anlyon.dev started tracking it. Last scanned Nov 12, 2026.

AI Website Summarizer MCP server

io.github.michaelvereb/aiwebsitesummarizermichaelverebstreamable-httpv1.0.1Scanned 3 days ago

Add an AI prompt widget to any website for AI SEO, GEO, and LLM mentions.

3 tools: 1 change things and 2 only read.

Reads private data · 2
Reads text others write · 3
Can send data out · 1
1 finding

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

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.dev only lists and labels, and these labels are the same either way.

What the AI Website Summarizer MCP server can do

The AI Website Summarizer MCP server is published by the GitHub account michaelvereb. It has 3 tools. It can create or change data (1 tool: get_ai_prompt_links), but cannot delete data. 2 tools only read.

2 tools read private data (get_ai_prompt_links and get_integration_docs); 3 tools bring in text other people can write (get_widget_embed_code, get_ai_prompt_links and get_integration_docs); 1 tool can send data out of your system (get_ai_prompt_links). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

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.

Last scanned Nov 12, 2026, version 1.0.1.

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.

3 tools

Changes things 1Creates or changes something that can be changed back.Claude Code: ask

get_ai_prompt_linksGenerate pre-built deep-link URLs that open ChatGPT, Claude, Gemini, or Grok pre-loaded with a custom prompt and page context for any given URL.Reads private dataReads text others writeCan send data out1 finding
Why it is in this group
- The name "get_ai_prompt_links" says "get": a word for reading.
- The description's first verb is "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
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "generate" and "chat": it reads messages, which other people 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.
Findings
- Warn
  The server marks "get_ai_prompt_links" 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 "get_ai_prompt_links" says "get": a word for reading.
  What this check looks for
Description, as the server wrote it
Generate pre-built deep-link URLs that open ChatGPT, Claude, Gemini, or Grok pre-loaded with a custom prompt and page context for any given URL.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true

Only reads 2Looks things up and changes nothing.Show 2 read-only tools

get_integration_docsRetrieve integration documentation, script attributes, configuration options, and SEO/GEO benefits of the AI Website Summarizer widget.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_integration_docs" says "get": a word for reading.
What it can reach
- private-dataThe name "get_integration_docs" says "get" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "retrieve" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it
Retrieve integration documentation, script attributes, configuration options, and SEO/GEO benefits of the AI Website Summarizer widget.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_widget_embed_codeGet the one-line script tag to add the AI Website Summarizer prompt widget to any website.Reads text others writeNo findings
Why it is in this group
- The name "get_widget_embed_code" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it
Get the one-line script tag to add the AI Website Summarizer prompt widget to any website. Supports optional color theme, widget position, and custom prompt prefix.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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.

6 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data2: Reads files, mail, messages, databases, secrets, calendars or repositories.; get_ai_prompt_links
get_integration_docs
Reads text others write3: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; get_ai_prompt_links
get_integration_docs
get_widget_embed_code
Can send data out1: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.; get_ai_prompt_links

deny to break every path

{
  "permissions": {
    "deny": [
      "mcp__aiwebsitesummarizer__get_ai_prompt_links"
    ]
  }
}

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 12, 2026, 10:20 UTC, unchanged since Nov 12, 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: 1
Protocol version: 2024-11-05
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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://www.aiwebsitesummarizer.com/mcp: tools/list returned 3 tools to an anonymous client, including get_ai_prompt_links (write)
What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn

Warnget_ai_prompt_links
The server marks "get_ai_prompt_links" 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 "get_ai_prompt_links" says "get": a word for reading.
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.

All changes to this server

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http aiwebsitesummarizer https://www.aiwebsitesummarizer.com/mcp

claude mcp add --transport http aiwebsitesummarizer https://www.aiwebsitesummarizer.com/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__aiwebsitesummarizer__get_widget_embed_code",
      "mcp__aiwebsitesummarizer__get_integration_docs"
    ],
    "ask": [
      "mcp__aiwebsitesummarizer__get_ai_prompt_links"
    ],
    "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 aiwebsitesummarizer. Review it before you use it.

Capability tags behind 3 rules

mcp__aiwebsitesummarizer__get_widget_embed_code untrusted-input
mcp__aiwebsitesummarizer__get_ai_prompt_links private-data, untrusted-input, outbound
mcp__aiwebsitesummarizer__get_integration_docs private-data, untrusted-input

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://anlyon.dev/api/v1/servers/io.github.michaelvereb/aiwebsitesummarizer/verify?hash=dc3261279b4d199c8cda8c88f729ecc4684b8a96e2411e5697ace2482fd24b86" | jq -e '.changed == false'

Pinned hash dc3261279b4d, from Nov 12, 2026, 03:18 UTC.

Watch

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

https://anlyon.dev/servers/io.github.michaelvereb/aiwebsitesummarizer/changes.xml

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

Badge

[![anlyon.dev](https://anlyon.dev/badge/io.github.michaelvereb/aiwebsitesummarizer.svg)](https://anlyon.dev/servers/io.github.michaelvereb/aiwebsitesummarizer)

Source: MCP Registry · repository. Synced Nov 12, 2026, 04:18 UTC.