A11y MCP는 LLM이 웹 접근성 테스트 API에 액세스할 수 있도록 하는 MCP(Model Context Protocol) 서버입니다.
이 서버는 Deque Axe-core API와 Puppeteer를 사용하여 LLM이 웹 콘텐츠를 분석하여 WCAG 규정을 준수하고 접근성 문제를 식별할 수 있도록 합니다.
참고: 이것은 Deque Labs의 공식 MCP 서버가 아닙니다.
프로젝트가 마음에 드셨다면 별점을 남겨주세요! 🌟
웹 페이지 테스트 : 모든 공개 URL의 접근성 문제를 테스트합니다.
HTML 스니펫 테스트 : 접근성 문제에 대한 원시 HTML 문자열 테스트
WCAG 준수 테스트 : 다양한 WCAG 표준(2.0, 2.1, 2.2)에 따라 콘텐츠를 확인합니다.
사용자 정의 가능한 테스트 : 테스트할 접근성 태그/표준을 지정합니다.
규칙 탐색 : 사용 가능한 접근성 규칙에 대한 정보 얻기
색상 대비 분석 : WCAG 규정 준수를 위한 색상 조합 확인
ARIA 검증 : ARIA 속성의 적절한 사용 테스트
방향 잠금 감지 : 특정 화면 방향을 강제로 지정하는 콘텐츠 식별
Related MCP server: @accesslint/mcp
Claude Desktop과 함께 이 서버를 사용하려면 MCP 설정에서 다음과 같이 구성해야 합니다.
macOS의 경우: '~/Library/Application Support/Claude/claude_desktop_config.json' 파일을 편집하세요.
지엑스피1
Windows의 경우: %APPDATA%\Claude\settings\claude_mcp_settings.json 파일을 편집하세요.
Linux의 경우: ~/.config/Claude/settings/claude_mcp_settings.json 파일을 편집합니다. /path/to/axe-mcp-server/build/index.js 컴파일된 서버 파일의 실제 경로로 바꿉니다.
URL의 접근성 문제를 테스트합니다.
매개변수:
url (필수): 테스트할 웹 페이지의 URL
tags (선택 사항): 테스트할 WCAG 태그 배열(예: ["wcag2aa"])
예
{
"url": "https://example.com",
"tags": ["wcag2aa"]
}HTML 문자열의 접근성 문제를 테스트합니다. 매개변수:
html(필수): 테스트할 HTML 콘텐츠
태그(선택 사항): 테스트할 WCAG 태그 배열(예: ["wcag2aa"])
예
{
"html": "<div><img src='image.jpg'></div>",
"tags": ["wcag2aa"]
}선택적 필터링을 통해 사용 가능한 접근성 규칙에 대한 정보를 얻으세요.
전경색과 배경색 조합이 WCAG 대비 요구 사항을 충족하는지 확인하세요.
매개변수:
foreground (필수): 16진수 형식의 전경색(예: "#000000")
background (필수): 16진수 형식의 배경색(예: "#FFFFFF")
fontSize (선택 사항): 픽셀 단위의 글꼴 크기(기본값: 16)
isBold (선택 사항): 텍스트를 굵게 표시할지 여부(기본값: false)
예
{
"foreground": "#777777",
"background": "#EEEEEE",
"fontSize": 16,
"isBold": false
}HTML에서 ARIA 속성이 올바르게 사용되었는지 확인하세요.
매개변수:
html (필수): ARIA 속성 사용을 테스트할 HTML 콘텐츠
예
{
"html": "<div role='button' aria-pressed='false'>Click me</div>"
}콘텐츠가 특정 방향을 강제로 표시하는지 확인하세요.
매개변수:
html (필수): 방향 잠금 문제를 테스트하기 위한 HTML 콘텐츠
예
{
"html": "<html><head><meta name='viewport' content='width=device-width, orientation=portrait'></head><body>Content</body></html>"
}서버는 구조화된 JSON 형식으로 접근성 테스트 결과를 반환합니다.
{
"violations": [
{
"id": "color-contrast",
"impact": "serious",
"description": "Ensure the contrast between foreground and background colors meets WCAG 2 AA minimum contrast ratio thresholds",
"help": "Elements must meet minimum color contrast ratio thresholds",
"helpUrl": "https://dequeuniversity.com/rules/axe/4.10/color-contrast",
"affectedNodes": [
{
"html": "<div style=\"color: #aaa; background-color: #eee;\">Low contrast text</div>",
"target": ["div"],
"failureSummary": "Fix any of the following: Element has insufficient color contrast of 1.98 (foreground color: #aaa, background color: #eee, font size: 12.0pt, font weight: normal)"
}
]
}
],
"passes": 1,
"incomplete": 0,
"inapplicable": 2,
"timestamp": "2025-04-25T16:45:33.655Z",
"url": "about:blank",
"testEngine": {
"name": "axe-core",
"version": "4.10.3"
},
"testRunner": {
"name": "axe"
},
"testEnvironment": {
"userAgent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) HeadlessChrome/135.0.0.0 Safari/537.36",
"windowWidth": 800,
"windowHeight": 600,
"orientationAngle": 0,
"orientationType": "portrait-primary"
}
}@modelcontextprotocol/sdk
인형극 배우
@axe-core/인형극단
도끼심
Check if ARIA attributes are used correctly in HTML
| Name | Required | Description | Default |
|---|---|---|---|
| html | Yes | HTML content to test for ARIA attribute usage |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool checks ARIA attribute correctness but does not describe what 'correctly' entails, the output format, error handling, or any performance considerations like rate limits. This leaves significant gaps in understanding the tool's behavior beyond its basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence: 'Check if ARIA attributes are used correctly in HTML.' It is front-loaded with the core purpose, avoids redundancy, and uses minimal words to convey essential information, making it highly efficient and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for effective tool use. It does not explain what constitutes correct ARIA usage, the format of results, or any behavioral traits like whether it's read-only or has side effects. For a tool with no structured metadata, the description should provide more context to compensate, but it falls short.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'html' parameter clearly documented as 'HTML content to test for ARIA attribute usage.' The description adds no additional semantic details beyond this, such as examples of valid HTML or constraints on input size. Given the high schema coverage, a baseline score of 3 is appropriate, as the schema adequately handles parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Check if ARIA attributes are used correctly in HTML.' It specifies the verb ('check'), resource ('ARIA attributes'), and context ('in HTML'), making the function unambiguous. However, it does not explicitly differentiate from sibling tools like 'test_accessibility' or 'test_html_string', which might have overlapping accessibility testing functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It lacks any mention of prerequisites, exclusions, or comparisons to sibling tools such as 'check_color_contrast' or 'get_rules', leaving the agent to infer usage context solely from the tool name and description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check if a foreground and background color combination meets WCAG contrast requirements
| Name | Required | Description | Default |
|---|---|---|---|
| background | Yes | Background color in various formats (e.g., "#FFFFFF", "#FFF", "rgb(255,255,255)", "hsv(0,0%,100%)") | |
| fontSize | No | Font size in pixels | |
| foreground | Yes | Foreground color in various formats (e.g., "#000000", "#000", "rgb(0,0,0)", "hsv(0,0%,0%)") | |
| isBold | No | Whether the text is bold |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While it states what the tool does (checking WCAG contrast requirements), it doesn't describe what specific WCAG levels are checked (AA/AAA), whether the tool provides detailed failure reasons, what the return format looks like, or any performance characteristics. For a tool with zero annotation coverage, this represents significant gaps in behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the core purpose without any wasted words. It's appropriately sized for a straightforward validation tool and gets directly to the point without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (color contrast validation with 4 parameters) and the absence of both annotations and an output schema, the description is minimally complete. It states what the tool does but doesn't provide information about return values, error conditions, or specific WCAG criteria checked. The description would need to do more heavy lifting to compensate for the lack of structured metadata.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents all 4 parameters. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. The baseline score of 3 is appropriate when the schema does all the parameter documentation work.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Check if...meets WCAG contrast requirements') and identifies the resources involved ('foreground and background color combination'). It distinguishes this tool from sibling tools like 'check_aria_attributes' or 'test_html_string' by focusing specifically on color contrast validation rather than broader accessibility testing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context (WCAG compliance checking for color combinations) but doesn't explicitly state when to use this tool versus alternatives like 'test_accessibility' or 'get_rules'. No guidance is provided about when NOT to use this tool or about prerequisites for effective use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check if content forces a specific orientation
| Name | Required | Description | Default |
|---|---|---|---|
| html | Yes | HTML content to test for orientation lock issues |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. The description only states what the tool does ('check if content forces a specific orientation') without detailing behavioral traits such as what 'forces' means, how orientation is determined, error handling, or output format. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence: 'Check if content forces a specific orientation.' It is front-loaded with the core purpose, has zero wasted words, and is appropriately sized for the tool's complexity. Every part of the sentence earns its place by conveying essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete. It does not explain what the tool returns (e.g., a boolean, a report, or error messages), how orientation lock is detected, or any behavioral nuances. For a tool with no structured behavioral data, the description should provide more context to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'html' parameter clearly documented as 'HTML content to test for orientation lock issues.' The description does not add any additional meaning beyond this schema, such as examples or constraints. With high schema coverage, the baseline score of 3 is appropriate as the schema handles the parameter documentation adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Check if content forces a specific orientation.' It uses a specific verb ('check') and identifies the resource ('content') and the specific issue ('orientation lock'). However, it does not explicitly differentiate from sibling tools like 'test_accessibility' or 'test_html_string,' which might also involve content testing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It does not mention sibling tools like 'test_accessibility' or 'test_html_string,' nor does it specify contexts or exclusions for usage. The tool's purpose is clear, but usage context is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get information about available accessibility rules with optional filtering
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Filter rules by these tags (e.g., "wcag2a", "wcag2aa", "best-practice") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'Get information', implying a read-only operation, but doesn't clarify aspects like whether it requires authentication, has rate limits, returns paginated results, or what the output format is. This leaves significant gaps in understanding how the tool behaves beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the purpose and key feature ('optional filtering') without any wasted words. It's front-loaded and appropriately sized for the tool's complexity, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for a tool that likely returns structured data about accessibility rules. It doesn't explain what information is returned, how results are formatted, or any behavioral traits like error handling. This leaves the agent with insufficient context to use the tool effectively beyond basic invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'tags' parameter well-documented in the schema itself. The description adds 'optional filtering', which aligns with the schema but doesn't provide additional semantic context beyond what's already specified. This meets the baseline for high schema coverage, but no extra value is added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and resource ('information about available accessibility rules'), making the purpose understandable. However, it doesn't differentiate this tool from its siblings like 'test_accessibility' or 'check_aria_attributes', which might also involve accessibility rules, so it doesn't fully distinguish itself from alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes 'optional filtering', which implies some context for usage, but it doesn't provide explicit guidance on when to use this tool versus its siblings. There's no mention of alternatives, prerequisites, or specific scenarios where this tool is preferred, leaving the agent with minimal direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Test a webpage for accessibility issues using Axe-core
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Optional array of accessibility tags to test (e.g., "wcag2a", "wcag2aa", "wcag21a") | |
| url | Yes | URL of the webpage to test |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states what the tool does but doesn't describe how it behaves: no information about execution time, error handling, rate limits, authentication requirements, or what constitutes a successful test. For a tool that performs analysis on external URLs, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states the core functionality without unnecessary words. It's appropriately sized for a tool with two parameters and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that performs accessibility testing on webpages with no annotations and no output schema, the description is insufficient. It doesn't explain what kind of results to expect, how issues are reported, whether the tool performs full-page analysis or sampling, or any limitations of the Axe-core engine. The context signals indicate this is a non-trivial analysis tool that needs more complete documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with both parameters well-documented in the schema itself. The description doesn't add any meaningful parameter semantics beyond what's already in the schema - it doesn't explain the relationship between URL and tags, provide examples of tag usage, or clarify testing scope. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Test') and resource ('a webpage for accessibility issues'), and mentions the technology used ('using Axe-core'). However, it doesn't explicitly differentiate from sibling tools like 'check_color_contrast' or 'test_html_string', which appear to be related accessibility testing functions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'test_html_string' or 'check_color_contrast'. It doesn't mention prerequisites, limitations, or typical use cases beyond the basic functionality.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Test an HTML string for accessibility issues
| Name | Required | Description | Default |
|---|---|---|---|
| html | Yes | HTML content to test | |
| tags | No | Optional array of accessibility tags to test (e.g., "wcag2a", "wcag2aa", "wcag21a") |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. While 'Test' implies a read-only analysis operation, the description doesn't specify what happens during testing, what kind of output to expect, whether there are rate limits, or any other behavioral characteristics beyond the basic purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that efficiently communicates the core purpose without any wasted words. It's appropriately sized for a tool with two parameters and gets straight to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a testing tool with no annotations and no output schema, the description provides the basic purpose but lacks important context about what the testing entails, what results to expect, and how it differs from related tools. The 100% schema coverage helps, but more behavioral context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema description coverage, the schema already documents both parameters thoroughly. The description adds no additional parameter information beyond what's in the schema, so it meets the baseline expectation but doesn't provide extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Test') and resource ('HTML string for accessibility issues'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'test_accessibility' or 'check_aria_attributes', which appear to be related accessibility testing tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives like 'test_accessibility' or the various 'check_' tools. The description only states what the tool does, not when it's appropriate or what distinguishes it from similar tools on the server.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0check_aria_attributescheck_color_contrastcheck_orientation_lockget_rulestest_accessibilitytest_html_stringScored across 6 tools
Each tool has a clearly distinct purpose: checking specific ARIA attributes, color contrast, orientation lock, retrieving rule information, testing webpages, and testing HTML strings. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., check_aria_attributes, test_accessibility). This predictability enhances readability and usability without any deviations or mixed conventions.
With 6 tools, the server is well-scoped for accessibility testing, covering key areas like ARIA, color contrast, orientation, rule retrieval, and testing methods. Each tool earns its place without feeling thin or bloated, aligning perfectly with the domain's needs.
The toolset provides comprehensive coverage for accessibility testing, including specific checks, rule information, and testing capabilities. A minor gap exists in lacking explicit tools for remediation or detailed reporting, but core workflows are fully supported, allowing agents to work effectively.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Cloudflare Workers MCP server: a11y-scorer
