Web Accessibility MCP Server
An MCP server that provides web accessibility analysis capabilities using axe-core and Puppeteer.
Web Accessibility MCP Server
An MCP (Model Context Protocol) server that provides web accessibility analysis capabilities using axe-core and Puppeteer.
Features
- Analyze web accessibility of any URL using axe-core
- Simulate color blindness (protanopia, deuteranopia, tritanopia) using color matrices
- Detailed reporting of accessibility violations
- Support for custom user agents and selectors
- Debug logging for troubleshooting
- Comprehensive accessibility checks based on WCAG guidelines
Prerequisites
- Node.js (v14 or higher)
- npm
Installation
Installing via Smithery
To install Web Accessibility MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @bilhasry-deriv/mcp-web-a11y --client claude
Manual Installation
- Clone the repository:
git clone [repository-url]
cd mcp-web-a11y
- Install dependencies:
npm install
- Build the server:
npm run build
Configuration
Add the server to your MCP settings file (typically located at ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json):
{
"mcpServers": {
"web-a11y": {
"command": "node",
"args": ["/path/to/mcp-web-a11y/build/index.js"],
"disabled": false,
"autoApprove": [],
"env": {
"MCP_OUTPUT_DIR": "/path/to/output/directory"
}
}
}
}
Environment Variables
MCP_OUTPUT_DIR: Directory where screenshot outputs will be saved- Required for the
simulate_colorblindtool - If not specified, defaults to './output' relative to the current working directory
- Must be an absolute path when configured in MCP settings
- Required for the
Usage
The server provides two tools: check_accessibility for analyzing web accessibility and simulate_colorblind for simulating color blindness.
Tool: check_accessibility
Checks the accessibility of a given URL using axe-core.
Parameters
url(required): The URL to analyzewaitForSelector(optional): CSS selector to wait for before analysisuserAgent(optional): Custom user agent string for the request
Example Usage
<use_mcp_tool>
<server_name>mcp-web-a11y</server_name>
<tool_name>check_accessibility</tool_name>
<arguments>
{
"url": "https://example.com",
"waitForSelector": ".main-content",
"userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
</arguments>
</use_mcp_tool>
Tool: simulate_colorblind
Simulates how a webpage appears to users with different types of color blindness using color matrix transformations.
Color Blindness Types
The tool supports three types of color blindness simulation:
-
Protanopia (red-blind) - Uses matrix:
0.567, 0.433, 0 0.558, 0.442, 0 0, 0.242, 0.758 -
Deuteranopia (green-blind) - Uses matrix:
0.625, 0.375, 0 0.7, 0.3, 0 0, 0.3, 0.7 -
Tritanopia (blue-blind) - Uses matrix:
0.95, 0.05, 0 0, 0.433, 0.567 0, 0.475, 0.525
Parameters
url(required): The URL to capturetype(required): Type of color blindness to simulate ('protanopia', 'deuteranopia', or 'tritanopia')outputPath(optional): Custom path for the screenshot outputuserAgent(optional): Custom user agent string for the request
Example Usage
<use_mcp_tool>
<server_name>mcp-web-a11y</server_name>
<tool_name>simulate_colorblind</tool_name>
<arguments>
{
"url": "https://example.com",
"type": "deuteranopia",
"outputPath": "colorblind_simulation.png"
}
</arguments>
</use_mcp_tool>
Response Format
check_accessibility Response
{
"url": "analyzed-url",
"timestamp": "ISO-timestamp",
"violations": [
{
"impact": "serious|critical|moderate|minor",
"description": "Description of the violation",
"help": "Help text explaining the issue",
"helpUrl": "URL to detailed documentation",
"nodes": [
{
"html": "HTML of the affected element",
"failureSummary": "Summary of what needs to be fixed"
}
]
}
],
"passes": 42,
"inapplicable": 45,
"incomplete": 3
}
simulate_colorblind Response
{
"url": "analyzed-url",
"type": "colorblind-type",
"outputPath": "path/to/screenshot.png",
"timestamp": "ISO-timestamp",
"message": "Screenshot saved with [type] simulation"
}
Error Handling
The server includes comprehensive error handling for common scenarios:
- Network errors
- Invalid URLs
- Timeout issues
- DNS resolution problems
Error responses will include detailed messages to help diagnose the issue.
Development
Project Structure
mcp-web-a11y/
├── src/
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript
├── output/ # Generated screenshots
├── package.json # Project dependencies and scripts
└── tsconfig.json # TypeScript configuration
Building
npm run build
This will:
- Compile TypeScript to JavaScript
- Make the output file executable
- Place the compiled files in the
builddirectory
Debugging
The server includes detailed debug logging that can be observed in the console output. This includes:
- Network requests and responses
- Page loading status
- Selector waiting status
- Any console messages from the analyzed page
- Color simulation progress
Common Issues and Solutions
-
Timeout Errors
- Increase the timeout value in the code
- Check network connectivity
- Verify the URL is accessible
-
DNS Resolution Errors
- Verify the URL is correct
- Check network connectivity
- Try using the www subdomain
-
Selector Not Found
- Verify the selector exists on the page
- Wait for dynamic content to load
- Check the page source for the correct selector
-
Color Simulation Issues
- Ensure the page's colors are specified in a supported format (RGB, RGBA, or HEX)
- Check if the page uses dynamic color changes (may require additional wait time)
- Verify the screenshot output directory exists and is writable
Contributing
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
相关服务器
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
GitGuardian
Scan projects for over 500 types of secrets using GitGuardian's API to prevent credential leaks.
zig-mcp
MCP server for Zig that connects AI coding assistants to ZLS (Zig Language Server) via LSP — 16 tools for code intelligence, build, and test.
Agent Loop
An AI Agent with optional Human-in-the-Loop Safety and Model Context Protocol (MCP) integration.
Linear Regression MCP
Train a Linear Regression model by uploading a CSV dataset file, demonstrating an end-to-end machine learning workflow.
x402engine
50+ pay-per-call APIs for AI agents via HTTP 402 crypto micropayments. $0.001–$0.12 per call with USDC and USDm.
open-context
A high-performance MCP server providing up-to-date documentation for Go, npm, Python, Rust, Docker, Kubernetes, Terraform, and more — fetched from official sources, not training data.
Claude Code Guardian
AI-Safe Code Analysis with 113+ MCP tools for guard validation, memory, workflow, and testing.
Shrike Security
AI agent security scanner — protect LLM-powered apps from prompt injection, SQL injection, data exfiltration, and adversarial attacks via MCP.
OriginUI MCP Server
Search and install OriginUI components, with details fetched dynamically from the OriginUI JSON registry.
OpenAPI2MCP
Converts OpenAPI specifications into MCP tools, enabling AI clients to interact with external APIs seamlessly.
