An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect AI Feature Accessibility Scorer to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Know exactly where your product fails WCAG standards.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through AI Accessibility Scorer.

  1. 01

    Analyze content description

    Evaluates the quality of text descriptions generated by the AI for visual assets

  2. 02

    Check navigation flow

    Validates if the AI interaction patterns are usable via keyboard

  3. 03

    Get compliance gaps

    Retrieves a detailed list of specific failures against the selected WCAG standard

  4. 04

    Calculate feature score

    Provides the primary high-level accessibility health assessment for a specific AI feature

Real work

What teams actually run

01

Pre-Launch Audit

Before releasing a new AI capability, run a full audit to get a feature score and check the navigation flow. This prevents a public failure.

02

Image Generation Review

When your AI generates images, use the content description capability to ensure the alt text is rich and detailed enough.

03

Compliance Reporting

Need to prove WCAG adherence? Use the gap identification capability to pull a detailed list of every technical failure.

04

UX Iteration

After a round of user testing, run the navigation flow check to see if the new interaction patterns are still keyboard accessible.

One connector, every AI

AI Accessibility Scorer works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put AI Accessibility Scorer to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

902ms average. Fast in production.

AI Accessibility Scorer is checked daily against the live service.

Daily averagePeak 1037ms
Oct 3Today
Fastest day
807ms
Slowest day
1037ms
14-day trend
Stable-3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of AI Accessibility Scorer, so you can see the experience inside your AI.

It does not authenticate your account with AI Accessibility Scorer. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

AI Accessibility Scorer Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_rV2BpIxzG7NdjZiOF2bymyAgpzUXW5625eSX7XqP/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — AI Accessibility Scorer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "ai-feature-accessibility-scorer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_rV2BpIxzG7NdjZiOF2bymyAgpzUXW5625eSX7XqP/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up AI Accessibility Scorer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work AI Accessibility Scorer owners hand off.

Product Managers and UX Designers use this MCP to validate that new AI features meet WCAG standards before launch. Developers rely on it to get specific, actionable failure reports. Compliance officers use it to prove that the product is accessible to the widest possible audience.

  • 01

    UX Designer

    Checks navigation flow and content descriptions to ensure the user experience is usable for all clients.

  • 02

    Product Manager

    Gets a high-level feature score and compliance gaps to determine if a feature is ready for market.

  • 03

    Developer

    Uses the capability to pinpoint specific technical failures and fix them before QA testing begins.

  • 04

    Compliance Officer

    Generates reports proving adherence to WCAG standards for regulatory audits.

FAQ

Questions AI Accessibility Scorer owners ask.

  • 01

    Does this MCP only check for WCAG AA compliance?

    The MCP analyzes compliance against WCAG standards. You can run checks to identify specific technical failures against the selected WCAG standard.

  • 02

    What kind of output do I get from the feature score?

    The output is a high-level health assessment score, plus a list of specific compliance gaps that need attention.

  • 03

    Can I check if my AI-generated alt text is good enough?

    Yes. The analyze_content_description capability evaluates the quality of text descriptions for visual assets, telling you if they are sufficient.

  • 04

    What is a 'focus trap' in this context?

    A focus trap is a navigation issue where a user, using only a keyboard, gets stuck in a part of the interface and cannot tab out of it. The check_navigation_flow capability detects these.

  • 05

    Is this capability for general accessibility or specific AI features?

    It is specialized for AI-driven software features. It provides diagnostic capabilities to evaluate the accessibility of AI interactions, not just static web pages.

  • 06

    How is the accessibility score calculated?

    The score is a weighted aggregate of WCAG compliance, navigation efficiency, and the quality of AI-generated content descriptions via calculate_feature_score.

  • 07

    Can I check if my AI's image descriptions are good enough?

    Yes, use the analyze_content_description capability to evaluate how well an AI-generated description captures the visual context for non-visual users.

  • 08

    How do I identify specific WCAG failures?

    You can use get_compliance_gaps to retrieve a detailed report of specific failures against your selected technical standard.

Explore

More in Accessibility

Suggestions

Connect AI Accessibility Scorer to Claude, Cursor, ChatGPT & more