mcpField
M
Mmnt

Mmnt

Local
github.com/zbkmSearch0Updated 82w ago
Repository

About Mmnt

Mmnt is an MCP server for searching the Mamont search engine and retrieving cached search-result pages. It provides separate tools for submitting a query and fetching a cached page by ID.

Key features

  1. 01Search Mamont by query and page
  2. 02Retrieve cached pages by ID
  3. 03Return cached pages as text or HTML

Use cases

  1. 01Search for information through Mamont
  2. 02Read a cached result page
  3. 03Retrieve cache content as text without HTML

MCP support

Exposes the `mmnt_search` and `mmnt_cache` tools to MCP clients. The cache tool can return text-only content or HTML.

#mmnt#mcp#server#search-engine

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "mmnt": {
      "command": "npx",
      "args": [
        "-y",
        "mmnt-mcp-server"
      ]
    }
  }
}
Run commandnpx -y mmnt-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmmnt-mcp-server

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
querystringYesquery string
pagenumberYespage number

Details

From the project README

mmnt-mcp-server

MCP server for the Mamont search engine.

Tools:
  • mmnt_search
    • search query on search engine
    • inputs
      • query - query string
      • page - page number
  • mmnt_cache
    • retrieve page from search page cache
    • inputs
      • id - unique cache id
      • onlyText - should the result be text only (no html)
Install
{
  "mcpServers": {
    "mmnt": {
      "command": "npx",
      "args": ["-y", "mmnt-mcp-server"]
    }
  }
}

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.