Skip to main content
Crawl your website and generate a properly formatted sitemap.xml file for search engines and AI assistants.

​
Overview

generate_sitemap creates a complete sitemap:
  • Automated crawling — discovers pages by following links
  • Configurable depth — scan up to 200 URLs
  • Spec-compliant XML — follows sitemap.xml standards
  • Priority and frequency hints — helps search engines understand your site
  • Ready to deploy — returns XML you can paste into /sitemap.xml
This tool is completely free and works without an API key.

​
Parameters

​
url
string
required
Your website URL (domain or full URL). The crawler starts here and follows internal links.
​
max_urls
number
default:"200"
Maximum number of URLs to include in the sitemap. Set lower for faster generation or higher for comprehensive coverage.

​
Example prompts

Generate a sitemap for my site

My sitemap is missing — create one

Create a sitemap.xml for https://example.com

​
Response structure

The tool returns a JSON object with:
​
xml
string
The complete sitemap.xml content, ready to deploy at /sitemap.xml
​
url_count
number
Number of URLs included in the sitemap
​
pages_by_type
object
Breakdown of URLs by content type (homepage, blog posts, pages, etc.)
​
crawl_date
string
When the crawl was performed

​
Usage example

# How the tool is called in the MCP server
@mcp.tool(annotations=READ_ONLY)
def generate_sitemap(url: str, max_urls: int = 200) -> str:
    """Create a sitemap.xml by crawling your website's pages."""
    client = _get_client()
    return _call(client.generate_sitemap, url, max_urls=max_urls)

​
Generated sitemap format

Example sitemap.xml output: 
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
  <url>
    <loc>https://example.com/</loc>
    <lastmod>2024-02-28</lastmod>
    <changefreq>weekly</changefreq>
    <priority>1.0</priority>
  </url>
  <url>
    <loc>https://example.com/blog/article-1</loc>
    <lastmod>2024-02-20</lastmod>
    <changefreq>monthly</changefreq>
    <priority>0.8</priority>
  </url>
  <!-- more URLs... -->
</urlset>

​
When to use

Use generate_sitemap when:
  • audit_site shows sitemap is missing — most common trigger
  • New site launch — ensure discoverability from day one
  • Major site restructure — regenerate after adding/removing pages
  • Dynamic content added — update when adding new sections
Run this regularly (monthly) to keep your sitemap up-to-date as you add new content.

​
Deployment

After generating the sitemap:
  1. Copy the xml from the response
  2. Save it as sitemap.xml at your domain root
  3. Deploy to https://yourdomain.com/sitemap.xml
  4. Verify it’s accessible publicly
  5. Add to your robots.txt: 
    Sitemap: https://yourdomain.com/sitemap.xml
  6. Submit to Google Search Console
The sitemap must be at your domain root (/sitemap.xml) or referenced in robots.txt.

​
Crawling behavior

The crawler:
  • Starts at the provided URL
  • Follows all internal links (same domain)
  • Respects robots.txt rules
  • Stops at max_urls limit
  • Excludes common non-content paths (admin, login, search)
  • Prioritizes important pages (homepage, main sections)
The crawler only finds pages linked from other pages. Orphan pages (not linked anywhere) won’t be included.

​
Sitemap best practices

  • Update regularly — regenerate monthly or after major content changes
  • Keep it focused — only include important, indexable pages
  • Add to robots.txt — reference your sitemap location
  • Submit to search engines — Google Search Console, Bing Webmaster Tools
  • Monitor coverage — check search console for indexing issues

​
Next steps