Summary
A second index, plus the cache behind it.
Two tools: search, and fetch what the engine already stored. The cache matters more than it sounds — when a result points at a page that has changed or gone, the cached copy is the version the index was built from.
What it is
An MCP server for the Mamont search engine at mmnt.ru, published to npm and runnable with npx.
What you get
- A search query run against Mamont, with paging through the results
- A page retrieved from the search engine's cache by its cache ID
- Cached pages returned as text only, with HTML stripped, when that is what you want to read
Requirements
Nothing — no account, no key. Node, to run it with `npx -y mmnt-mcp-server`.
Setup effort
One command — npx -y mmnt-mcp-server