Check Links

An MCP server that analyzes websites for broken links, missing meta tags, and redirect chains. Returns a structured report with a health score and fix suggestions.

What it does

• Checks all links on a page for 4xx/5xx errors (up to 20 links)
• Detects missing meta tags: title, description, og:title, og:description, og:image, canonical, viewport
• Traces redirect chains and flags excessive hops
• Returns a score (0–100) and actionable suggestions

Install

npx mcp-check-links

Configure in Claude Code

Add to your .claude/settings.json (or ~/.claude/settings.json):

{
  "mcpServers": {
    "check-links": {
      "command": "npx",
      "args": ["mcp-check-links"],
      "env": {
        "MCPCAT_PROJECT_ID": "proj_your_id_here"
      }
    }
  }
}

Or if running locally from the built output:

{
  "mcpServers": {
    "check-links": {
      "command": "node",
      "args": ["/path/to/mcp-check-links/dist/index.js"],
      "env": {
        "MCPCAT_PROJECT_ID": "proj_your_id_here"
      }
    }
  }
}

MCPCAT_PROJECT_ID is optional. Get your project ID from mcpcat.io. The server runs fine without it — analytics are simply disabled.

Analytics

This server supports MCPcat analytics. Set the MCPCAT_PROJECT_ID environment variable to your project ID (e.g. proj_abc123xyz) to enable usage tracking, session replay, and error monitoring. Without it, the server runs normally with no analytics.

See the MCPcat setup guide for details on creating a project and getting your ID.

Tool

check-links

Input: { "url": "https://example.com" }

Output:

{
  "url": "https://example.com",
  "brokenLinks": [{"href": "...", "status": 404, "text": "..."}],
  "missingMetaTags": ["og:image", "canonical"],
  "presentMetaTags": {"title": "...", "description": "..."},
  "redirectChain": ["https://example.com -> https://www.example.com"],
  "score": 85,
  "suggestions": ["Add og:image meta tag", "Fix broken link (404): /old-page"]
}