mcpbeat

Lattis MCP Server

dev.lattis/mcp
answering

Lattis is answering right now. Last checked moments ago. 50 installs a week from npm. It exposes 5 tools.

Search indexed websites, read raw page markdown, and score AI visibility for any site.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 28 · avg 7 · +85% w/w
a month agotoday
Uptime history 39 hours of history
39 hours agonow
100.0%
Uptime 24h
92 of 92 checks
5
Tools
read from the server
284 ms
Response time
average over 24h
50
Installs / week
npm and PyPI

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add mcp --transport http https://mcp.lattis.dev/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.lattis.dev/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcp]
url = "https://mcp.lattis.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.lattis.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.lattis.dev/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

sitedex
sitedex_get_page
The full markdown of one page on an indexed site. Use it after `search` points you at a URL and you want the whole page.
sitedex_get_site
Site profile and headline AI Visibility Score for one domain — name, description, category, page count, the buyer questions the site answers, and which AI-readable artifacts (`llms.txt`, MCP card, WebMCP manifest, JSON-LD) the owner has installed.
sitedex_list_pages
Paths Sitedex has indexed on a domain — title, URL, path. Use it to browse a site's structure before searching or fetching.
sitedex_list_sites
Every website Sitedex has indexed, with name, category, page count, and AI Visibility Score. Use it to discover what is available before searching.
sitedex_search
Search every indexed website. Returns ranked markdown passages with the source URL, heading path, and a relevance score. Pass `site` to scope to one domain.

Endpoints

URLTransportStateLatencyChecked
https://mcp.lattis.dev/mcp streamable-http answering 300 ms 0 min ago

Lattis — questions

Answers built from our own checks of this server.

What can Lattis do?
It exposes 5 tools, read directly from the server on our last check. Among them: sitedex_get_page, sitedex_get_site, sitedex_list_pages, sitedex_list_sites, sitedex_search. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Lattis working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 284 ms. The bar chart above shows every period we have measured.
Is Lattis still maintained?
The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect Lattis?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Lattis need an API key?
No. Lattis completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Lattis?
It answers our handshake in 284 ms on average, which is faster than 48% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Lattis?
The npm package @lattis-dev/cli was installed 50 times in the last week. Week over week that is +85%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.