Skip to content

Slop Patterns

by sloppatterns.com · remote · no sign-in to list tools · v1.2.1 · published by com.sloppatterns

Checks UI code for AI-default design patterns and gives the fix. By Precious Studio.

Changes · 3
CompareRegistry entry

7 tools: 3 change things and 4 only read.

Scanned Oct 21, 2026

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http slop-patterns https://sloppatterns.com/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • Warncheck_design

    The server marks "check_design" 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

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

7 tools

Changes things 3Claude Code: ask
  • changelogThe library version, what each release added or changed, and how patterns are versioned.No 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.
    Description, as the server wrote it
    The library version, what each release added or changed, and how patterns are versioned. Use it to cite a specific version of Slop Patterns.

    Annotations the server declares

    • title: Library changelog
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • check_designCheck a snippet of CSS, HTML or JSX against the Slop Patterns library and return every AI design anti-pattern it matches, with the fix for each.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_design" 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 snippet of CSS, HTML or JSX against the Slop Patterns library and return every AI design anti-pattern it matches, with the fix for each. Covers the 101 documented patterns that have a mechanical tell. Useful for reviewing generated UI code.

    Annotations the server declares

    • title: Check UI code for AI design patterns
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • report_patternReport an AI design anti-pattern that is NOT yet in the library, for a design failure seen repeatedly that a search of the library does not find.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Report an AI design anti-pattern that is NOT yet in the library, for a design failure seen repeatedly that a search of the library does not find. Reports are reviewed by a human before anything is published, and published entries credit the reporter.

    Annotations the server declares

    • title: Report a new pattern
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 4Claude Code: allow
  • get_patternGet one full pattern entry by id or code (e.g.No findings

    Why it is in this group

    • The name "get_pattern" says "get": a word for reading.
    Description, as the server wrote it
    Get one full pattern entry by id or code (e.g. "a1" or "the-unchosen-gradient"): what it looks like, why the tools produce it, who it hurts, the fix, sources.

    Annotations the server declares

    • title: Get one pattern
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • list_patternsList the whole Slop Patterns taxonomy: code, id, name and one-liner for every documented AI design anti-pattern.No findings

    Why it is in this group

    • The name "list_patterns" says "list": a word for reading.
    Description, as the server wrote it
    List the whole Slop Patterns taxonomy: code, id, name and one-liner for every documented AI design anti-pattern.

    Annotations the server declares

    • title: List all patterns
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • search_patternsPlain-language search across the library.No findings

    Why it is in this group

    • The name "search_patterns" says "search": a word for reading.
    Description, as the server wrote it
    Plain-language search across the library. "gradient headline" returns A10 Gradient Text Headline.

    Annotations the server declares

    • title: Search patterns
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • whyReturn only the causal explanation for one pattern — which model, tool or template default produces it.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return only the causal explanation for one pattern — which model, tool or template default produces it.

    Annotations the server declares

    • title: Why a pattern happens
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • 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.

Install

Pinned to version 1.2.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http slop-patterns https://sloppatterns.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__slop-patterns__list_patterns",
      "mcp__slop-patterns__get_pattern",
      "mcp__slop-patterns__search_patterns",
      "mcp__slop-patterns__why"
    ],
    "ask": [
      "mcp__slop-patterns__check_design",
      "mcp__slop-patterns__changelog",
      "mcp__slop-patterns__report_pattern"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as slop-patterns. Review it before you use it.