TypeScript MCP(모델 컨텍스트 프로토콜) 서버로, API 키 없이 직접 연결을 통한 포괄적인 웹 검색 기능을 제공하며, 다양한 사용 사례에 맞는 여러 도구를 제공합니다.

특징

• 다중 엔진 웹 검색: 최적의 신뢰성과 성능을 위해 빙> 브레이브 > 덕덕고를 우선시함
• 전체 페이지 콘텐츠 추출: 검색 결과에서 전체 페이지 콘텐츠를 가져오고 추출함
• 다중 검색 도구: 다양한 사용 사례를 위한 세 가지 전문 도구
• 스마트 요청 전략: 극작가 브로워스와 빠른 액시오스 요청을 전환하여 결과를 반환합니다
• 동시 처리: 여러 페이지에서 동시에 콘텐츠를 추출

작동 원리

서버는 다양한 웹 검색 필요에 맞는 세 가지 전문 도구를 제공합니다:

1. full-web-search (주 도구)

포괄적인 검색이 요청될 때, 서버는 최적화된 검색 전략을 사용합니다:

1. 브라우저 기반 빙 검색 - 전용 Chromium 인스턴스를 사용하는 주요 방법
2. 브라우저 기반 Brave Search - 전용 Firefox 인스턴스를 사용하는 보조 옵션
3. Axios DuckDuckGo Search - 전통적인 HTTP를 이용한 최종 대체

Web Search MCP Server for use with Local LLMs

A TypeScript MCP (Model Context Protocol) server that provides comprehensive web search capabilities using direct connections (no API keys required) with multiple tools for different use cases.

Features

• Multi-Engine Web Search: Prioritises Bing > Brave > DuckDuckGo for optimal reliability and performance
• Full Page Content Extraction: Fetches and extracts complete page content from search results
• Multiple Search Tools: Three specialised tools for different use cases
• Smart Request Strategy: Switches between playwright browesrs and fast axios requests to ensure results are returned
• Concurrent Processing: Extracts content from multiple pages simultaneously

How It Works

The server provides three specialised tools for different web search needs:

1. full-web-search (Main Tool)

When a comprehensive search is requested, the server uses an optimised search strategy:

1. Browser-based Bing Search - Primary method using dedicated Chromium instance
2. Browser-based Brave Search - Secondary option using dedicated Firefox instance
3. Axios DuckDuckGo Search - Final fallback using traditional HTTP
4. Dedicated browser isolation: Each search engine gets its own browser instance with automatic cleanup
5. Content extraction: Tries axios first, then falls back to browser with human behavior simulation
6. Concurrent processing: Extracts content from multiple pages simultaneously with timeout protection
7. HTTP/2 error recovery: Automatically falls back to HTTP/1.1 when protocol errors occur

2. get-web-search-summaries (Lightweight Alternative)

For quick search results without full content extraction:

1. Performs the same optimised multi-engine search as full-web-search
2. Returns only the search result snippets/descriptions
3. Does not follow links to extract full page content

3. get-single-web-page-content (Utility Tool)

For extracting content from a specific webpage:

1. Takes a single URL as input
2. Follows the URL and extracts the main page content
3. Removes navigation, ads, and other non-content elements

Compatibility

This MCP server has been developed and tested with LM Studio and LibreChat. It has not been tested with other MCP clients.

Model Compatibility

Important: Prioritise using more recent models designated for tool use.

Older models (even those with tool use specified) may not work or may work erratically. This seems to be the case with Llama and Deepseek. Qwen3 and Gemma 3 currently have the best restults.

• ✅ Works well with: Qwen3
• ✅ Works well with: Gemma 3
• ✅ Works with: Llama 3.2
• ✅ Works with: Recent Llama 3.1 (e.g 3.1 swallow-8B)
• ✅ Works with: Recent Deepseek R1 (e.g 0528 works)
• ⚠️ May have issues with: Some versions of Llama and Deepseek R1
• ❌ May not work with: Older versions of Llama and Deepseek R1

Installation (Recommended)