Skip to content

Front-End Checklist MCP server

io.github.thedaviddias/front-end-checklistthedaviddiasstreamable-httpv2.0.1Scanned

Review frontend code and live pages against 386 quality-gated web development rules.

11 tools: 2 change things and 9 only read.

Tools: 0 delete, 0 irreversible, 2 write, 9 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • 2 findings

Tools listed without sign-in. Remote posture

Anlyon alternative

2 of these tools change something. Run those 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 Radar 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 →

What the Front-End Checklist MCP server can do

The Front-End Checklist MCP server is published by the GitHub account thedaviddias. It has 11 tools. It can create or change data (2 tools: review_code and check_rule), but cannot delete data. 9 tools only read.

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

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 20, 2026, version 2.0.1.

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.

11 tools

Changes things 2Claude Code: ask
  • check_ruleChecks a code snippet against one named frontend rule using static heuristics and returns findings and verification guidance.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_rule" 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
    Checks a code snippet against one named frontend rule using static heuristics and returns findings and verification guidance. Without code, returns manual verification guidance. Use it when the user requests a check of a specific rule or a proposed fix. Results do not establish rendered-state or runtime conformance.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Check Rule Compliance
  • review_codeRuns a non-exhaustive static heuristic review of pasted HTML, CSS, or JavaScript against multiple frontend best practices and returns prioritized issues, fix guidance, and suggesti…1 finding

    Why it is in this group

    • The description's first verb is "run": a word for a change.
    • 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 "review_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 description's first verb is "run": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Runs a non-exhaustive static heuristic review of pasted HTML, CSS, or JavaScript against multiple frontend best practices and returns prioritized issues, fix guidance, and suggestions for manual verification. Use it when the user requests a review, audit, or debugging of source code. An empty issue list means no provable static issue was found; it does not establish accessibility conformance or runtime correctness.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Review Frontend Code
Only reads 9Show 9 read-only tools
  • audit_urlFetches a public HTTPS page and performs a non-exhaustive static review of its HTML, returning prioritized issues and fix guidance.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The description's first verb is "fetch": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "audit_url" says "url": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "fetch" and "http": it reads web pages, which anyone 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.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Fetches a public HTTPS page and performs a non-exhaustive static review of its HTML, returning prioritized issues and fix guidance. Use it when the user requests an audit of a deployed public page. Localhost, private networks, and plain HTTP URLs are refused. It does not execute the page, measure live Core Web Vitals, or certify accessibility.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • title: Audit Live URL
  • explain_ruleExplains one frontend rule, including its background, impact on users and the business, and related categories.No findings

    Why it is in this group

    • The name "explain_rule" says "explain": a word for reading.
    Description, as the server wrote it
    Explains one frontend rule, including its background, impact on users and the business, and related categories. Use it when the user asks why a practice matters or requests educational context. It returns explanation guidance rather than applying a fix.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Explain Frontend Rule
  • fix_ruleReturns step-by-step remediation guidance and priority for one named frontend rule.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
    Returns step-by-step remediation guidance and priority for one named frontend rule. Use it when the user requests implementation or fix instructions for a known issue. Optional codeSnippet provides context; the tool does not edit files or apply changes.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Rule Fix
  • get_checklist_rulesReturns titles, priorities, verification and remediation prompts for every rule in a curated checklist.No findings

    Why it is in this group

    • The name "get_checklist_rules" says "get": a word for reading.
    Description, as the server wrote it
    Returns titles, priorities, verification and remediation prompts for every rule in a curated checklist. Use it when the user requests guidance for an entire checklist. includeContent optionally adds each rule’s long-form body. Available checklists: accessibility-essentials, comprehensive-audit, core-web-vitals, html-foundations, image-optimization, javascript-resilience, launch-checklist, performance-quick-wins, privacy-and-consent, security-audit, seo-audit, testing-checklist.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Checklist Rules
  • get_quick_referenceReturns a compact checklist for one frontend category, filtered by priority and formatted as JSON, Markdown, or a task list.No findings

    Why it is in this group

    • The name "get_quick_reference" says "get": a word for reading.
    Description, as the server wrote it
    Returns a compact checklist for one frontend category, filtered by priority and formatted as JSON, Markdown, or a task list. Use it when the user requests a concise checklist for a deployment, review, or team handoff.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Quick Reference
  • get_ruleReturns complete guidance for one known rule slug: requirements, rationale, verification and remediation prompts, code examples, sources, and related rules.No findings

    Why it is in this group

    • The name "get_rule" says "get": a word for reading.
    Description, as the server wrote it
    Returns complete guidance for one known rule slug: requirements, rationale, verification and remediation prompts, code examples, sources, and related rules. Use it when the user requests detailed guidance for a specific frontend rule. Unknown slugs return similar suggestions.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Rule Guidance
  • get_workflowReturns the ordered steps of a curated audit workflow, including rule slugs, priorities, and categories.No findings

    Why it is in this group

    • The name "get_workflow" says "get": a word for reading.
    Description, as the server wrote it
    Returns the ordered steps of a curated audit workflow, including rule slugs, priorities, and categories. Use it when the user requests a structured audit such as a pre-launch checklist. Available workflows: accessibility-essentials, comprehensive-audit, core-web-vitals, html-foundations, image-optimization, javascript-resilience, launch-checklist, performance-quick-wins, privacy-and-consent, security-audit, seo-audit, testing-checklist.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Get Audit Workflow
  • list_categoriesLists available frontend rule categories, their descriptions, and rule counts.No findings

    Why it is in this group

    • The name "list_categories" says "list": a word for reading.
    Description, as the server wrote it
    Lists available frontend rule categories, their descriptions, and rule counts. Use it when the user asks what the checklist covers or needs valid category names.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: List Rule Categories
  • search_rulesFinds frontend rules by keywords, category, and priority, returning paginated slugs, titles, and short summaries.No findings

    Why it is in this group

    • The name "search_rules" says "search": a word for reading.
    Description, as the server wrote it
    Finds frontend rules by keywords, category, and priority, returning paginated slugs, titles, and short summaries. Use it when the user requests relevant practices for a technology, concern, or pattern, such as web fonts or accessible forms.

    Annotations the server declares

    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • title: Search Frontend Rules

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, 19:12 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
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.frontendchecklist.io/.well-known/oauth-protected-resource
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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.frontendchecklist.io: tools/list returned 11 tools to an anonymous client, including review_code (write), check_rule (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

2 warn
  • The server marks "review_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 description's first verb is "run": a word for a change.

    What this check looks for
  • The server marks "check_rule" 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 2.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http front-end-checklist https://mcp.frontendchecklist.io
claude mcp add --transport http front-end-checklist https://mcp.frontendchecklist.io

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__front-end-checklist__get_workflow",
      "mcp__front-end-checklist__get_checklist_rules",
      "mcp__front-end-checklist__get_quick_reference",
      "mcp__front-end-checklist__get_rule",
      "mcp__front-end-checklist__search_rules",
      "mcp__front-end-checklist__fix_rule",
      "mcp__front-end-checklist__explain_rule",
      "mcp__front-end-checklist__list_categories"
    ],
    "ask": [
      "mcp__front-end-checklist__review_code",
      "mcp__front-end-checklist__audit_url",
      "mcp__front-end-checklist__check_rule"
    ],
    "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 front-end-checklist. Review it before you use it.

Capability tags behind 1 rule
  • mcp__front-end-checklist__audit_url 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/io.github.thedaviddias/front-end-checklist/verify?hash=e23dcfb11f5a6286193a079528f5f1a69a033b7db00ab2463655929290c33667" | jq -e '.changed == false'

Pinned hash e23dcfb11f5a, from Nov 20, 2026, 15:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.thedaviddias/front-end-checklist/changes.xml

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

Badge

Anlyon Radar badge for io.github.thedaviddias/front-end-checklist
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.thedaviddias/front-end-checklist.svg)](https://radar.anlyon.com/servers/io.github.thedaviddias/front-end-checklist)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.

Front-End Checklist MCP server: questions and answers

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

Is the Front-End Checklist MCP server safe?

No scan can promise that. What its definitions show: 11 tools, 2 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 Front-End Checklist MCP server delete data?

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

Can the Front-End Checklist 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 Front-End Checklist MCP server have?

11 tools: 2 write, 9 read. review_code, check_rule, audit_url, get_workflow, get_checklist_rules, get_quick_reference, get_rule, search_rules and 3 more.

Does the Front-End Checklist MCP server need sign-in or OAuth?

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

Does the Front-End Checklist 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): audit_url.

Has the Front-End Checklist MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.