How to Use the Accessibility Prover MCP in Mastra AI

Automate WCAG 2.2 AA validation inside your Mastra AI workflows and auto-retry failed UI builds before deployment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Accessibility Prover MCP to Mastra AI

Create your Vinkius account to connect Accessibility Prover to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Accessibility Prover with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-retry failed accessibility checks in Mastra AI pipelines

Mastra AI excels at running complex, multi-step agentic workflows. When your agent builds a new UI layout, you can pipe the output directly into the `validate_accessibility` tool. If the validation fails due to a bad contrast ratio or missing keyboard tab order, the workflow engine automatically triggers a retry. Your agent receives the exact error logs from the MCP Server and attempts to fix the markup. It recalculates the contrast to hit the 4.5:1 threshold and re-evaluates the code. This loop continues until the component passes validation, meaning you never deploy broken layouts.

Human-in-the-loop approval for EAA 2025 compliance

Some accessibility decisions require a human eye, and Mastra AI makes this easy to configure. You can set up your workflow to run the `validate_accessibility` tool first, checking semantic HTML landmarks and motion media queries. If the tool flags a complex modal trap, the workflow pauses and requests manual approval. This prevents automated agents from making bad assumptions about screen reader navigation. Developers can review the agent's proposed ARIA annotations directly in their Slack or internal dashboard. Once approved, the workflow resumes and deploys the validated component.

Strict validation of complex state transitions

Interactive state changes often break keyboard accessibility, especially during dynamic updates. This MCP Server forces your Mastra AI agents to explicitly map out focus indicators and modal traps before building. The tool rejects any design that relies on div click handlers without proper keyboard fallback support. By enforcing these rules at the workflow level, you guarantee that every dynamic state transition remains accessible. Your agents are forced to write robust CSS overrides for transitions using prefers-reduced-motion. You get reliable, compliant UI components that match European accessibility laws.

Setup guide

Set up Accessibility Prover MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Accessibility Prover tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "accessibility-prover-mcp-client",
  servers: {
    "accessibility-prover-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Accessibility Prover Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Accessibility Prover tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Accessibility Prover transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Accessibility Prover. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Accessibility Prover now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Accessibility Prover MCP in Mastra AI

You configure a conditional branch in your workflow. If the `validate_accessibility` tool returns a rejection, Mastra AI routes the payload back to the generator agent with the error logs. The agent then fixes the contrast ratios or ARIA labels and tries again.

Yes, you can gate the workflow using the tool approval settings. When the MCP Server detects a complex screen reader pattern, Mastra AI can pause the execution. This lets a developer manually check the proposed alt texts and focus paths before the component is built.

Yes, when integrated with Mastra AI, you can leverage the framework's built-in exponential backoff. If the validation tool fails due to a temporary network blip or API limit, the client retries the request automatically. This keeps your automated deployment pipelines running smoothly.

No, Vinkius hosts and manages the MCP Server for you. You don't have to deal with Docker files or server maintenance. Just copy your Vinkius endpoint URL, initialize the client in your Mastra config, and start validating your components.

Your UI design specifications, HTML landmarks, and CSS motion overrides are processed in a highly secure, zero-trust V8 isolate sandbox on Vinkius. The data is parsed in memory to run the WCAG check and is instantly destroyed once the validation response is sent back to Mastra AI.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript