get_sitemap_treeLABSCO SUMMARY
A site's shape in one call.
How many pages a site has and how they are arranged, answered from its published sitemap — the question that otherwise means a crawler and an afternoon.
What it is
A Python server that fetches and parses a website's sitemap and returns it as a tree. Structural questions about any site — page counts, section hierarchy, pages that exist but are not linked from the navigation — are answered from what the site already publishes.
What you get
- get_sitemap_tree fetches a site's sitemap and returns the URL hierarchy
- Nothing is crawled: the answer comes from the sitemap the site publishes for search engines
- Ships prompt templates for Claude Desktop — analyze a website, check sitemap health, extract URLs, find missing content, visualize the structure — each taking just a URL
Requirements
uv, and uvx sitemap-mcp-server in the client config with TRANSPORT set to stdio. No account or key: it reads sitemaps that are already public.
Setup effort
One command — uvx sitemap-mcp-server
USE CASES
01
Finding out how big a site really is
A page count and the hierarchy behind it, which settles scoping questions before a migration or an audit starts.
02
Mapping a competitor's site structure
The sections they publish, and how deep each one goes, without touching their servers beyond one sitemap fetch.
03
Finding pages that are published but not linked
The sitemap lists what the site tells search engines exists, which is often more than the navigation shows.
04
Checking your own sitemap before you rely on it
Reading back what you actually publish is the fastest way to catch a sitemap that has gone stale or half-empty.
4 tools
Listed in project docs. Your client may show a different list.
get_sitemap_pagesget_sitemap_statsparse_sitemap_contentBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
uvx on PATH
INSTALLATION
Connect your client
Server setup
TERMINAL
uvx sitemap-mcp-serverMCP Clients
Claude Desktop, Cursor, Windsurf
JSON
{
"mcpServers": {
"sitemap": {
"command": "uvx",
"args": [
"sitemap-mcp-server"
],
"env": {
"TRANSPORT": "stdio"
}
}
}
}Cursor — SSE
Start the server in a terminal and leave it running:
CURSOR — SSE · TERMINAL
uvx sitemap-mcp-serverThen add this to Cursor's MCP settings:
CURSOR — SSE · JSON
{
"mcpServers": {
"sitemap": {
"url": "http://localhost:8050/sse"
}
}
}
