Maibaamcrawler

Name: Maibaamcrawler
Author: MABAAM

@MABAAM

リポジトリ

Maibaamcrawler について

MCP_crawlertool

#web-search #research #web-scraping #maibaam

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

MABAAM

投稿者

phimonic

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "research": {
      "command": "uvx",
      "args": [
        "mcp-research"
      ],
      "env": {
        "BRAVE_API_KEY": "",
        "OLLAMA_URL": ""
      }
    }
  }
}

ツール

Search the web using a 3-tier cascade (Brave → DuckDuckGo → scraper). Args: query: Search query string. max_results: Maximum number of results to return (1-20). summarize: If true and Ollama is available, summarize the results. auto_fetch_top: If true, also fetch the full content of the top result.

Fetch a URL, convert to markdown. SSRF-protected and cached. Args: url: The URL to fetch. summarize: If true and Ollama is available, include a summary. max_chars: Maximum characters of content to return.

Compound research: search → fetch top pages → summarize → synthesize. Args: query: The research question. depth: Research depth — "quick" (2 pages), "standard" (5 pages), or "deep" (10 pages). context: Optional context from prior research to inform synthesis.

概要

What is Maibaamcrawler?

Maibaamcrawler is an MCP server that provides eight read-only tools for web research, academic paper retrieval, Twitter/X extraction, YouTube video analysis, and file ingestion. It integrates with the MCP stdio protocol to enable AI assistants to perform research tasks.

How to use Maibaamcrawler?

Install the mcp-research package via pip install mcp-research or run directly with uvx mcp-research. Configure environment variables like BRAVE_API_KEY and OLLAMA_URL, then add the server to your MCP client configuration (e.g., Claude Code or Claude Desktop). Use the CLI commands such as mcp-research search or mcp-research doctor for direct interaction.