Accessibility Scanner MCP Server
Accessibility Scanner MCP servers enable AI models to perform WCAG compliance checks, capture annotated screenshots, and generate detailed accessibility reports.
Overview
The MCP Accessibility Scanner is a powerful Model Context Protocol (MCP) server that provides automated web accessibility scanning using Playwright and Axe-core. This server enables LLMs to perform WCAG compliance checks, interact with web pages, manage persistent browser sessions, and generate detailed accessibility reports with visual annotations.
Created by:
Developed by Justas Monkevicius
Key Features
WCAG Compliance Checking
Full WCAG 2.0/2.1/2.2 compliance checking (A, AA, AAA levels)
Annotated Screenshots
Automatic screenshot capture with violation highlighting
Detailed JSON Reports
Detailed JSON reports with remediation guidance
Specific Violation Categories
Support for specific violation categories (color contrast, ARIA, forms, keyboard navigation, etc.)
Available Tools
Quick Reference
| Tool | Purpose | Category |
|---|---|---|
scan_page | Performs a comprehensive accessibility scan on the current page | Accessibility |
browser_navigate | Navigate to a URL | Navigation |
browser_navigate_back | Go back to the previous page | Navigation |
browser_navigate_forward | Go forward to the next page | Navigation |
browser_snapshot | Capture accessibility snapshot of the current page | Page Interaction |
browser_click | Perform click on a web page element | Page Interaction |
browser_type | Type text into editable element | Page Interaction |
browser_hover | Hover over element on page | Page Interaction |
browser_drag | Perform drag and drop between two elements | Page Interaction |
browser_select_option | Select an option in a dropdown | Page Interaction |
browser_press_key | Press a key on the keyboard | Page Interaction |
browser_take_screenshot | Take a screenshot of the current page | Screenshot & Visual |
Detailed Usage
scan_page▶
Performs a comprehensive accessibility scan on the current page using Axe-core.
use_mcp_tool({
server_name: "accessibility-scanner",
tool_name: "scan_page",
arguments: {
violationsTag: ["wcag21aa", "cat.color"]
}
});
Supported Violation Tags: wcag2a, wcag2aa, wcag2aaa, wcag21a, wcag21aa, wcag21aaa, wcag22a, wcag22aa, wcag22aaa, section508, cat.aria, cat.color, cat.forms, cat.keyboard, cat.language, cat.name-role-value, cat.parsing, cat.semantics, cat.sensory-and-visual-cues, cat.structure, cat.tables, cat.text-alternatives, cat.time-and-media
browser_navigate▶
Navigate to a URL.
use_mcp_tool({
server_name: "accessibility-scanner",
tool_name: "browser_navigate",
arguments: {
url: "https://example.com"
}
});
browser_click▶
Perform click on a web page element.
use_mcp_tool({
server_name: "accessibility-scanner",
tool_name: "browser_click",
arguments: {
element: "Login button",
ref: "#login-btn"
}
});
browser_type▶
Type text into editable element.
use_mcp_tool({
server_name: "accessibility-scanner",
tool_name: "browser_type",
arguments: {
element: "Email input",
ref: "#email",
text: "[email protected]"
}
});
Installation
{
"mcpServers": {
"accessibility-scanner": {
"command": "npx",
"args": [
"-y",
"mcp-accessibility-scanner"
]
}
}
}
Sources
Related Articles
Tasks Organizer MCP Server
A local Model Context Protocol (MCP) server providing backend tools for client-driven project and task management using a SQLite database.
YouTube Research MCP Server
YouTube Research MCP servers enable AI models to interact with YouTube content, providing capabilities for video information retrieval, transcript management, channel analysis, and playlist management.
Ollama Deep Researcher: AI Model for Web Search & LLM Synthesis
Ollama Deep Researcher MCP servers enable AI models to perform advanced topic research using web search and LLM synthesis, powered by a local MCP server.