Skip to content

Design Check MCP server

com.allthepossibles/designcheckallthepossibles.comstreamable-httpv1.0.0Scanned

Scores whether a page reads as AI-generated and names the tells to fix.

3 tools: 3 change things.

Tools: 0 delete, 0 irreversible, 3 write, 0 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • 2 findings

Tools listed without sign-in. Remote posture

With Anlyon

3 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 Design Check MCP server can do

The Design Check MCP server is published by allthepossibles.com, a domain the MCP Registry verified. It has 3 tools. It can create or change data (3 tools: check_design, check_copy and check_code), but cannot delete data. None of its tools only reads.

1 tool brings in text other people can write (check_design); 1 tool can send data out of your system (check_design).

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 12, 2026, version 1.0.0.

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 3Claude Code: ask
  • check_codeCheck a source file or diff for AI 'tells' left in comments: narrating fulfilling a request instead of describing the code ("as requested," "I've added," "here's the updated versio…1 finding

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.code), which can change anything it can reach.

      What this check looks for
    Description, as the server wrote it
    Check a source file or diff for AI 'tells' left in comments: narrating fulfilling a request instead of describing the code ("as requested," "I've added," "here's the updated version") and hedge words. These reveal there was a conversation behind the change that a later reader has no access to. Call this before committing or shipping code an agent wrote.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_copyCheck marketing or outreach copy (an email, a landing-page draft, a pitch, a social post) for the tells that make it read as AI-generated: cliché vocabulary (delve, unlock, empower…1 finding

    Why it is in this group

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

    Findings

    • Warn

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

      Matched text

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

      What this check looks for
    Description, as the server wrote it
    Check marketing or outreach copy (an email, a landing-page draft, a pitch, a social post) for the tells that make it read as AI-generated: cliché vocabulary (delve, unlock, empower, seamlessly integrate, etc.), negative-parallel framing ("not just X, but Y"), hedge words, heavy em-dash use, and diagnosing a problem with no fix in the same breath. No page or markup needed, just the text. Call this before sending copy to a human.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_designCheck a page's HTML/CSS/copy/interaction for the patterns that make AI-generated work read as generic: default fonts, soft tech gradients, pill+arrow buttons, eyebrow labels, a com…Reads text others writeCan send data outNo 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.
    • 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
    Check a page's HTML/CSS/copy/interaction for the patterns that make AI-generated work read as generic: default fonts, soft tech gradients, pill+arrow buttons, eyebrow labels, a composition with no real width/background variation across sections, uniform card grids, copy tells (AI vocabulary, negative-parallel framing, hedge words, heavy em-dash use), and experience gaps (a diagnosis with no next step, dead-end links). Every finding includes a concrete fix. Call this before presenting UI to a human.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
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 20, 2026, 18:33 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
3
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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://designcheck.allthepossibles.com/mcp: tools/list returned 3 tools to an anonymous client, including check_design (write), check_copy (write), check_code (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

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

    Matched text

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

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

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The input takes a statement or command to run (input.code), which can change anything it can reach.

    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 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http designcheck https://designcheck.allthepossibles.com/mcp
claude mcp add --transport http designcheck https://designcheck.allthepossibles.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": [],
    "ask": [
      "mcp__designcheck__check_design",
      "mcp__designcheck__check_copy",
      "mcp__designcheck__check_code"
    ],
    "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 designcheck. Review it before you use it.

Capability tags behind 1 rule
  • mcp__designcheck__check_design untrusted-input, outbound

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.allthepossibles/designcheck/verify?hash=c0a8eac545795aff210e8255578324b018bf8dab37a2fed273d7ffb386f14ce7" | jq -e '.changed == false'

Pinned hash c0a8eac54579, from Nov 12, 2026, 14:17 UTC.

Watch

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

https://radar.anlyon.com/servers/com.allthepossibles/designcheck/changes.xml

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

Badge

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

Source: MCP Registry. Synced Oct 21, 2026, 17:48 UTC.

Design Check MCP server: questions and answers

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

Is the Design Check MCP server safe?

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

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

Can the Design Check 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 Design Check MCP server have?

3 tools: 3 write. check_design, check_copy and check_code.

Does the Design Check MCP server need sign-in or OAuth?

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

Does the Design Check 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): check_design.

Has the Design Check MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.