mmnt_searchLABSCO 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
USE CASES
01
Searching an index other tools do not cover
Run the query against Mamont and page through the results.
02
Reading a page that has since changed
Pull the cached copy by its ID rather than the live page.
03
Getting readable text out of a result
Ask for the cached page as text only, so the HTML does not come with it.
2 tools
Listed in project docs. Your client may show a different list.
mmnt_cacheBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
npx on PATH
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mmnt": {
"command": "npx",
"args": [
"-y",
"mmnt-mcp-server"
]
}
}
}npx
TERMINAL
npx -y mmnt-mcp-server
