Lattis
Search indexed websites, read raw page markdown, and score AI visibility for any site.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mcp": {
"url": "https://mcp.lattis.dev/mcp"
}
}
}Remote endpoints
https://mcp.lattis.dev/mcpstreamable-httpWhat it can do
Tool inventory
Tools (5)
🟢sitedex_search(query, site, top_k)
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.
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"minLength": 1,
"maxLength": 4000,
"description": "What you are trying to find, e.g. 'does PostHog have a SOC2 report' or 'stripe webhook signature verification'"
},
"site": {
"type": "string",
"description": "Optional: scope to a single domain, e.g. 'posthog.com' or 'supabase.com'"
},
"top_k": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "How many passages to return (default 20, max 50)"
}
},
"required": [
"query"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢sitedex_list_sites(limit)
Every website Sitedex has indexed, with name, category, page count, and AI Visibility Score. Use it to discover what is available before searching.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500,
"description": "Max sites to return (default 200, max 500)"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢sitedex_get_site(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.
Input Schema
{
"type": "object",
"properties": {
"site": {
"type": "string",
"description": "Domain ('posthog.com') or slug ('posthog-com')"
}
},
"required": [
"site"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢sitedex_list_pages(site, limit)
Paths Sitedex has indexed on a domain — title, URL, path. Use it to browse a site's structure before searching or fetching.
Input Schema
{
"type": "object",
"properties": {
"site": {
"type": "string",
"description": "Domain or slug to list pages for"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500
}
},
"required": [
"site"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢sitedex_get_page(site, path)
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.
Input Schema
{
"type": "object",
"properties": {
"site": {
"type": "string",
"description": "Domain ('posthog.com') or slug"
},
"path": {
"type": "string",
"description": "Page path starting with /, e.g. '/pricing' or '/docs/api'"
}
},
"required": [
"site",
"path"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}Community
Evidence