Skip to main content
Glama
Heventure Search MCP

Heventure Search MCP

by HughesCuit

中文 | 한국어


MCP 웹 검색 서버

DuckDuckGo, Bing, Google을 지원하고 향상된 검색 품질을 위해 SerpAPI/Tavily를 선택적으로 사용할 수 있는 무료 API 키가 필요 없는 웹 검색 MCP(Model Context Protocol) 서버입니다.

기능

  • 🔍 멀티 엔진 검색: DuckDuckGo + Bing + Google (무료, API 키 불필요)

  • 🔑 선택적 API 키: 더 나은 검색 품질을 위한 SerpAPI 및 Tavily 지원

  • 📄 웹 콘텐츠 가져오기: 모든 웹페이지에서 텍스트 콘텐츠 추출

  • 🚀 비동기 처리: 고성능 asyncio 기반 비동기 처리

Related MCP server: Web Search MCP Server

설치

PyPI (권장)

pip install heventure-search-mcp
heventure-search-mcp

uvx

uvx heventure-search-mcp

소스에서 설치

pip install git+https://github.com/HughesCuit/heventure-search-mcp.git
python -m server

사용법

MCP 클라이언트 설정

{
  "mcpServers": {
    "web-search": {
      "command": "python",
      "args": ["/path/to/server.py"]
    }
  }
}

Trae AI

{
  "mcpServers": {
    "heventure-search-mcp": {
      "command": "uvx",
      "args": ["heventure-search-mcp"]
    }
  }
}

사용 가능한 도구

web_search

여러 엔진으로 웹 콘텐츠를 검색합니다.

매개변수:

  • query (문자열, 필수): 검색어

  • max_results (정수, 선택): 최대 결과 수 (기본값: 10, 범위: 1-20)

  • search_engine (문자열, 선택): 엔진 선택 (기본값: "both")

    • "duckduckgo": DuckDuckGo 전용

    • "bing": Bing 전용

    • "google": Google 전용

    • "both": DuckDuckGo + Google + Bing

선택적 API 키 (향상된 검색용)

유료 검색 엔진을 활성화하기 위해 환경 변수를 선택적으로 설정할 수 있습니다:

# SerpAPI (Google search results via API, 100 searches/month free)
export SERPAPI_KEY="your_serpapi_key"

# Tavily (AI-optimized search, 1000 searches/month free)
export TAVILY_API_KEY="your_tavily_api_key"

API 키가 구성되면 무료 엔진과 함께 자동으로 사용되어 검색 품질을 향상시킵니다.

예시:

{
  "query": "Python tutorial",
  "max_results": 5,
  "search_engine": "both"
}

get_webpage_content

웹페이지에서 텍스트 콘텐츠를 가져옵니다.

매개변수:

  • url (문자열, 필수): 대상 웹페이지 URL

예시:

{
  "url": "https://example.com"
}

오류 처리

  • 네트워크 실패 시 자동 재시도

  • 구문 분석 오류 시 정상적인 성능 저하(Graceful degradation)

  • 사용자 친화적인 오류 메시지

라이선스

MIT 라이선스

기여

이슈 및 풀 리퀘스트는 언제나 환영합니다!

Available Tools

2 tools
get_webpage_contentA

Extract readable text content from a specific webpage URL. Use this tool after web_search when you need the full text of a page found in search results. The tool strips scripts, styles, and navigation elements, returning only the meaningful text content. Output is truncated to 2000 characters to stay within context limits. Returns an empty string if the page cannot be fetched or parsed.

Inputs: url (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one searches the web, the other retrieves content from a specific URL. There is no overlap in functionality, and their descriptions make the differentiation explicit.

    Naming Consistency5/5

    Both tool names follow a consistent verb_noun pattern: 'web_search' and 'get_webpage_content'. The naming is clear, predictable, and uses underscores consistently.

    Tool Count4/5

    With only two tools, the server is minimal but well-scoped for a search-and-retrieve workflow. While more tools could be added (e.g., for advanced filtering or caching), the current count fits the server's stated purpose without being too thin.

    Completeness5/5

    The tool set covers the basic search workflow: find pages via web_search, then extract content via get_webpage_content. There are no obvious gaps for the intended use case of retrieving text from web pages.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables browser automation using Puppeteer through the MCP interface. Allows launching browsers, creating pages, and executing arbitrary JavaScript for web scraping, testing, and debugging tasks.
      5
      119 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables web search across multiple search engines (DuckDuckGo, Bing, Startpage) with parallel execution and result deduplication. Also provides web page content extraction capabilities.
      2
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables web searching through Google, DuckDuckGo, and Bing using a headless Chrome browser, returning structured results with titles, URLs, and snippets. Also supports fetching and extracting text content from any webpage.
      16
      MIT