MyA11yReport MCP
mya11y.report- Category
- Developer Tools
- Rank
- No. 2601Tools index
Previous survey · No. 2549 ·
- Type
- TOOL
- Use case
- Software Testing & Quality
- Interfaces
- MCP
- Date
About
MyA11yReport MCP is a local Model Context Protocol server that gives an AI coding agent (Claude Desktop, Claude Code, opencode, and others) the ability to drive a real Chromium browser via Playwright and audit a web page: it runs axe-core violation scans, reports landmark and heading structure, tab and focus order, image alt text, and WCAG 2.2 contrast ratios, and lets the agent navigate, click, and screenshot pages itself. It runs entirely on the local machine with no account or API key, communicating with the agent over stdio.
At a glance
MyA11yReport MCP lets a coding agent inspect a page in Chromium and gather accessibility findings using axe-core and browser evidence. It is worth trying as a first pass when you need findings your agent can reproduce.
Good fit
Web developers checking a local test page before manual accessibility review.
Consider something else when
Use human testing when the question is whether a real user can complete a workflow with assistive technology.
Start here
Use a test page with one unlabeled control. Check that the report identifies it, then navigate the page by keyboard to find what the automated check missed.
Cost and requirements
The vendor documents a local MCP server that uses Playwright and Chromium and connects over standard input and output.
Limits to know
Automated findings cover the loaded page and tested state. The server runs locally according to the vendor, while a connected agent may send returned page evidence to its provider.
Sources checked 2026-11-05. Source-based assessment.
Tags
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.