Skip to content
MCP server

OverlayQA

Scan pages for accessibility and design-token issues, then file UI bugs from your editor

Pricing
Free trial
Platforms
CLI, Web, API
Runs
Locally or Remotely
Version
0.8.0
Listing updated
3 days ago

About OverlayQA

OverlayQA is an MCP server for developer tools. It can run locally on your machine or as a hosted remote server.

OverlayQA's server connects an AI coding agent to a UI bug tracker. Point it at a public URL and it runs a WCAG audit with axe-core, checks colour contrast, and scores how consistently the page uses design tokens for font sizes, colours, spacing, font families and border radii. It can then create an issue for every violation above a chosen severity.

Beyond scanning, the tools manage the tracker itself: create, read, filter, update, move and verify issues, plus labels, comments, projects and client reviews. Verification re-checks whether a resolved issue is fixed on its public page and saves a verdict without changing status. Auto Review and visual comparison against a Figma frame run as jobs with screenshot evidence.

On first run a browser tab opens to connect your OverlayQA account, and the connection lasts 30 days. Scans cannot use your signed-in browser session, so pages behind a login need Auto Review from the OverlayQA Chrome extension. The server runs over stdio or as a hosted endpoint; the site mentions 31 live tools while the README for version 0.8.0 lists 45, depending on rollout and permissions.

Install

Run in a terminal

claude mcp add --transport http mcp https://api.overlayqa.com/mcp

Add to Settings → Connectors → Add custom connector

https://api.overlayqa.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.overlayqa.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.overlayqa.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://api.overlayqa.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://api.overlayqa.com/mcp"
    }
  }
}

Tools this server provides (15)

Taken from the project documentation; the running server may differ.

scan_accessibility
WCAG audit with axe-core on a public URL
scan_contrast
Check colour-contrast ratios across a page
audit_tokens
Audit design-token usage with a 0-100 score
run_auto_review
Start an Auto Review of a public page
compare_visual
Compare a page against a Figma frame or design image
get_review_result
Read a review already started
scan_and_create_issues
Scan a URL and create issues for violations above a threshold
create_issue
Create an issue in a project
get_issue
Read a complete issue
list_issues
List and filter project issues
update_issue
Update issue fields or status
move_issue
Move an issue to another project
verify_issue
Check whether a resolved issue is fixed on its page
get_issue_verifications
Read saved verification results
list_labels
List the workspace label library

What it does

WCAG audit
Runs axe-core on a public URL with severity, criteria and an overall score.
Contrast check
Lists failing foreground and background pairs.
Design-token audit
Gives a 0-100 token-health score with findings.
Bulk issue creation
Creates issues for every violation above a severity threshold.
Issue tracking
Create, list, update, move and verify issues by UUID or display id.
Visual comparison
Compares a page to a Figma frame or design image with screenshot evidence.

Good for

  • Scan a staging site and open issues for the critical failures
  • Check whether a fixed bug is really fixed on the live page
  • Audit how consistently a page follows its design tokens
  • Compare a built page against its Figma design

Pricing

Free trial, from $39 a month

Starter $39/mo ($32/mo annual), Team $79/mo, Pro $249/mo; 14-day free trial.

Prices change. Check overlayqa.com before you buy.

OverlayQA FAQ

Does it need an account?

Yes. A browser tab opens on first run to connect your OverlayQA account, which the README calls free with no card.

Can it scan pages behind a login?

Not through URL scans; use Auto Review from the OverlayQA Chrome extension on that page.

What do plans cost?

Starter is $39 a month, or $32 billed annually, with a 14-day free trial.

How do I add it to Claude Code?

Run claude mcp add --scope user overlayqa -- npx -y @overlayqa/mcp@latest.

Is OverlayQA free?

OverlayQA is a paid product with a free trial. Paid plans start at $39 a month.

How do I add OverlayQA to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://api.overlayqa.com/mcp

What are the best alternatives to OverlayQA?

The closest alternatives to OverlayQA are REA, HyperFrames by HeyGen, Codebase Memory, GitHub and Serena MCP: the IDE for your agent.

Alternatives to OverlayQA

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Hosted MCP connector for creating and rendering videos from HTML through AI chat

    • Remote
    • Freemium
    • 85.3K GitHub stars
    • Design and media
  3. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  4. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  5. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  6. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory