Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Motivation and Context
The UUV MCP (Model Context Protocol) was designed to make accessibility-focused end-to-end testing more efficient, more consistent, and more accessible to both humans and AI agents.
Writing high-quality E2E tests that respect accessibility standards (ARIA roles, accessible names, semantic structure) is often complex, repetitive, and error-prone. It requires deep knowledge of both testing frameworks and accessibility specifications. The UUV MCP addresses this challenge by exposing a structured and intelligent interface that automates and standardizes the generation of UUV test scenarios in Gherkin format.
By providing dedicated tools such as
available_sentences,generate_role_and_name, andgenerate_table, the MCP enables:The UUV MCP Server acts as a bridge between human intent and executable accessibility tests, allowing users to describe what they want to validate (role, name, table structure) while the system produces structured, readable, and ready-to-run test scenarios.
In short, the UUV MCP exists to industrialize the creation of accessible E2E tests, ensuring that automation remains human-readable, accessibility-compliant, and seamlessly integrated into modern development and AI-driven workflows.
Many other tools are currently under development.
How Has This Been Tested?
Tested with:
Types of changes
Checklist
Additional context