ImageDimensions

Audit the images on any web page for AI agents: natural vs rendered dimensions, oversized-image detection, and format breakdown.

Documentation

imagedimensions-mcp

An MCP server that audits the images on any public web page — natural vs. rendered dimensions, oversized-image detection, and format breakdown — so AI agents (Claude, Cursor, Windsurf, etc.) can check image performance during development.

Powered by imagedimensions.com. The scan runs server-side, so no local browser or Chrome install is required.

Install / run

// Claude Desktop / any MCP client config
{
  "mcpServers": {
    "imagedimensions": {
      "command": "npx",
      "args": ["-y", "imagedimensions-mcp"]
    }
  }
}

Tool

scan_image_dimensions

ParamTypeDescription
urlstring (required)Public URL of the page to audit.
oversizedThresholdnumber (optional)Area-overshoot ratio to flag as oversized. Default 4 (≈2× per dimension).

Returns a text report plus structured content:

  • total / visible image counts and CSS-background count
  • modern-format share (WebP + AVIF)
  • format breakdown
  • the list of oversized images (natural → rendered, overshoot ratio, format, src)
  • a link to the full visual report on imagedimensions.com

Example agent uses: "Audit the images on https://example.com," "Which images on this page are oversized and hurting LCP?", "What % of this site's images use modern formats?"

Why "oversized" matters

An image downloaded much larger than the box it renders into wastes bandwidth and slows Largest Contentful Paint — the most common image-performance mistake on the web. See the writeup.

Config

  • IMAGEDIMENSIONS_API_BASE — override the API base (default https://imagedimensions.com).

License

MIT