Discover website architecture and analyze site structure by fetching, parsing, and visualizing sitemaps from any URL. Uncover hidden pages and
Sitemap MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Discover website architecture and analyze site structure by fetching, parsing, and visualizing sitemaps from any URL. Uncover hidden pages and extract organized hierarchies without manual exploration.
Once Sitemap is connected, these are the calls the assistant has available:
get_sitemap_tree — Fetch and parse the sitemap tree from a website URLArguments — url (website URL), include_pages (optional, boolean)Returns — JSON representation of the sitemap tree structureget_sitemap_pages — Get all pages from a website's sitemap with filtering optionsget_sitemap_stats — Get statistics about a website's sitemapparse_sitemap_content — Parse a sitemap directly from its XML or text contentTools — The Tools tool exposed by this serverPrompts — The server includes ready-to-use prompts that appear as templates in Claude Desktop. After installing the server, you'll see these templates in theExamples — The Examples tool exposed by this serverThe server ships on npm as @smithery/cli, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
You will need one environment variable: TRANSPORT. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Sitemap's toolset — get_sitemap_tree, Arguments, Returns and 6 more — is a fair guide to whether it matches your workflow. It is maintained by mugoosse; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| get_sitemap_tree | Fetch and parse the sitemap tree from a website URL |
| Arguments | url (website URL), include_pages (optional, boolean) |
| Returns | JSON representation of the sitemap tree structure |
| get_sitemap_pages | Get all pages from a website's sitemap with filtering options |
| get_sitemap_stats | Get statistics about a website's sitemap |
| parse_sitemap_content | Parse a sitemap directly from its XML or text content |
| Tools | The Tools tool exposed by this server. |
| Prompts | The server includes ready-to-use prompts that appear as templates in Claude Desktop. After installing the server, you'll see these templates in the "Templates" menu (click the + icon next to the message input): |
| Examples | The Examples tool exposed by this server. |
{
"mcpServers": {
"sitemap": {
"command": "uvx",
"args": ["sitemap-mcp-server"],
"env": { "TRANSPORT": "stdio" }
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| TRANSPORT | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.