Is the Michael Vereb MCP server safe?

No scan can promise that. What its definitions show: 7 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the Michael Vereb MCP server delete data?

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

Can the Michael Vereb 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 Michael Vereb MCP server have?

7 tools: 7 read. get_portfolio, get_case_study, get_testimonials, list_contact, search_articles, get_tools and get_ai_ui.

Does the Michael Vereb MCP server need sign-in or OAuth?

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

Does the Michael Vereb MCP server send data to outside services?

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

Has the Michael Vereb MCP server changed its tools?

Yes, once since anlyon.dev started tracking it, most recently on Nov 12, 2026. Every change is on this page and in its Atom feed.

Michael Vereb MCP server

io.github.michaelvereb/michaelverebmichaelverebstreamable-httpv1.0.2Scanned 3 days ago

Query portfolio case studies, verified developer tools, and the AI-UI design system.

7 tools: 7 only read.

Reads private data · 2
Reads text others write · 4
Can send data out · 0
No findings

Tools listed without sign-in. Remote posture

Anlyon alternative

Run the operations that matter as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

anlyon.dev does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Its sign-in does not let Anlyon set up an OAuth client on its own, so there is no link to it here.

What the Michael Vereb MCP server can do

The Michael Vereb MCP server is published by the GitHub account michaelvereb. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

2 tools read private data (list_contact and get_ai_ui); 4 tools bring in text other people can write (get_testimonials, list_contact, search_articles and 1 more).

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.dev first saw them.

Last scanned Nov 12, 2026, version 1.0.2.

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

Only reads 7Looks things up and changes nothing.Show 7 read-only tools

get_ai_uiOverview of the AI-UI design system (20 accessible Astro components for AI reasoning, execution pipelines, and streaming chat), package install instructions, and pointer to the ded…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_ai_ui" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it
Overview of the AI-UI design system (20 accessible Astro components for AI reasoning, execution pipelines, and streaming chat), package install instructions, and pointer to the dedicated sub-MCP server at https://www.michaelvereb.com/ai-ui/mcp.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_case_studyRetrieves detailed architecture, technical deliverables, and impact metrics for a specific client case study by company slug.No findings
Why it is in this group
- The name "get_case_study" says "get": a word for reading.
Description, as the server wrote it
Retrieves detailed architecture, technical deliverables, and impact metrics for a specific client case study by company slug.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_portfolioRetrieves client case studies and engineering projects.No findings
Why it is in this group
- The name "get_portfolio" says "get": a word for reading.
Description, as the server wrote it
Retrieves client case studies and engineering projects. Supports optional search query (by company name or topic) and limit parameter.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_testimonialsRetrieves verified client reviews, leadership testimonials, and stakeholder endorsements with author names, roles, and review quotes.Reads text others writeNo findings
Why it is in this group
- The name "get_testimonials" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "retrieve" and "review": it reads comments, which other people can write.
Description, as the server wrote it
Retrieves verified client reviews, leadership testimonials, and stakeholder endorsements with author names, roles, and review quotes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- untrustedContentHint: true
get_toolsRetrieves developer tools, open-source packages, and AI infrastructure created and maintained by Michael Vereb.No findings
Why it is in this group
- The name "get_tools" says "get": a word for reading.
Description, as the server wrote it
Retrieves developer tools, open-source packages, and AI infrastructure created and maintained by Michael Vereb.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_contactRetrieves verified contact channels, email address, LinkedIn profile, timezone, and direct scheduling links.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_contact" says "list": a word for reading.
What it can reach
- private-dataThe name "list_contact" says "list" and "contact": it reads contacts.
- private-dataThe description's first sentence says "retrieve" and "contact": it reads contacts.
- untrusted-inputThe description's first sentence says "retrieve" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it
Retrieves verified contact channels, email address, LinkedIn profile, timezone, and direct scheduling links.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
- untrustedContentHint: false
search_articlesSearches published technical articles, design system guides, and AI/SEO strategy posts by keyword.Reads text others writeNo findings
Why it is in this group
- The name "search_articles" says "search": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "search" and "post": it reads posts, which other people can write.
Description, as the server wrote it
Searches published technical articles, design system guides, and AI/SEO strategy posts by keyword.
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.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.

Reads private data2: Reads files, mail, messages, databases, secrets, calendars or repositories.; get_ai_ui
list_contact
Reads text others write4: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; get_ai_ui
get_testimonials
list_contact
search_articles
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 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: 0
Protocol version: 2024-11-05
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: not observed
RFC 9728 protected resource metadata: https://www.michaelvereb.com/.well-known/oauth-protected-resource
Authorization servers: https://www.michaelvereb.com
Legacy HTTP+SSE transport: no
Dynamic client registration: no
Client ID metadata documents: no

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.

Nov 12, 2026Tools7 changed.~7 changedView diff
- Changed:get_ai_uiOnly readsannotations
- Changed:get_case_studyOnly readsannotations
- Changed:get_portfolioOnly readsannotations
- Changed:get_testimonialsOnly readsannotations
- Changed:get_toolsOnly readsannotations
- Changed:list_contactOnly readsannotations
- Changed:search_articlesOnly readsannotations

All changes to this server

Install

Pinned to version 1.0.2. Values in angle brackets are yours to fill in.

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

claude mcp add --transport http michaelvereb https://www.michaelvereb.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__michaelvereb__get_portfolio",
      "mcp__michaelvereb__get_case_study",
      "mcp__michaelvereb__get_testimonials",
      "mcp__michaelvereb__list_contact",
      "mcp__michaelvereb__search_articles",
      "mcp__michaelvereb__get_tools",
      "mcp__michaelvereb__get_ai_ui"
    ],
    "ask": [],
    "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 michaelvereb. Review it before you use it.

Capability tags behind 4 rules

mcp__michaelvereb__get_testimonials untrusted-input
mcp__michaelvereb__list_contact private-data, untrusted-input
mcp__michaelvereb__search_articles untrusted-input
mcp__michaelvereb__get_ai_ui 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/michaelvereb/verify?hash=2b840afcc861d9f38dc7daf5bb7a2d033e78abdf5ff03f2cd49d0ee5974d5272" | jq -e '.changed == false'

Pinned hash 2b840afcc861, 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/michaelvereb/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/michaelvereb.svg)](https://anlyon.dev/servers/io.github.michaelvereb/michaelvereb)

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