Skip to main content
Glama

search-fusion-mcp

by sailaoda

πŸ” Search Fusion MCP Server

🌏 δΈ­ζ–‡ζ–‡ζ‘£

A High-Availability Multi-Engine Search Aggregation MCP Server providing intelligent failover, unified API, and LLM-optimized content processing. Search Fusion integrates multiple search engines with smart priority-based routing and automatic failover mechanisms.

πŸ†• What's New in v3.0.0: Major concurrency upgrade! Enhanced multi-threading support with thread-safe operations, intelligent connection pooling, and semaphore-based request limiting. Now supports 50+ concurrent searches without race conditions or data corruption!

✨ Features

πŸ”„ Multi-Engine Integration

  • Google Search - Premium performance with API key
  • Serper Search - Google search alternative with advanced features
  • Jina AI Search - AI-powered search with intelligent content processing
  • DuckDuckGo - Free search, no API key required
  • Exa Search - AI-powered semantic search
  • Bing Search - Microsoft search API
  • Baidu Search - Chinese search engine

πŸš€ Advanced Features

  • Intelligent Failover - Automatic engine switching on failures or rate limits
  • Priority-Based Routing - Smart engine selection based on availability and performance
  • Unified Response Format - Consistent JSON structure across all engines
  • Rate Limiting Protection - Built-in cooldown mechanisms
  • πŸ”„ High Concurrency Support - Thread-safe operations with connection pooling
  • ⚑ Performance Optimization - Async operations with semaphore-based concurrency control
  • LLM-Optimized Content - Advanced web content fetching with pagination support
  • Wikipedia Integration - Dedicated Wikipedia search tool
  • Wayback Machine - Historical webpage archive search
  • Environment Variable Configuration - Pure MCP configuration without config files
  • 🌐 Enhanced Proxy Auto-Detection - Intelligent proxy detection with zero configuration

πŸ“Š Monitoring & Analytics

  • Real-time engine status monitoring
  • Success rate tracking
  • Error handling and recovery
  • Performance metrics

⚑ Concurrency & Performance

  • Thread-Safe Operations - All engine statistics and state updates are protected by async locks
  • Connection Pooling - Shared HTTP client with configurable connection limits (max 100 connections)
  • Semaphore Control - Concurrent request limiting (max 30 simultaneous searches)
  • Timeout Protection - 60-second search timeout prevents request accumulation
  • Resource Management - Efficient memory usage with automatic connection cleanup
  • Race Condition Prevention - Double-checked locking for SearchManager initialization

πŸ—οΈ Architecture

Search Fusion MCP Server β”œβ”€β”€ πŸ”§ Configuration Manager # MCP environment variable handling β”œβ”€β”€ πŸ” Search Manager # Multi-engine orchestration with concurrency control β”œβ”€β”€ ⚑ Concurrency Layer # Thread-safe operations & performance optimization β”‚ β”œβ”€β”€ AsyncLock Protection # Thread-safe state updates β”‚ β”œβ”€β”€ HTTP Connection Pool # Shared client with connection limits β”‚ β”œβ”€β”€ Semaphore Control # Concurrent request limiting (max 30) β”‚ └── Timeout Management # 60s timeout protection β”œβ”€β”€ πŸš€ Engine Implementations # Individual search engines β”‚ β”œβ”€β”€ GoogleSearch # Google Custom Search β”‚ β”œβ”€β”€ SerperSearch # Serper API β”‚ β”œβ”€β”€ JinaSearch # Jina AI Search β”‚ β”œβ”€β”€ DuckDuckGoSearch # DuckDuckGo β”‚ β”œβ”€β”€ ExaSearch # Exa AI β”‚ β”œβ”€β”€ BingSearch # Bing API β”‚ └── BaiduSearch # Baidu API β”œβ”€β”€ πŸ› οΈ Advanced Fetcher # Multi-method web scraping └── πŸ“‘ MCP Server # FastMCP integration

πŸš€ Quick Start

Installation

pip install search-fusion-mcp
Option 2: Install from Source
git clone https://github.com/sailaoda/search-fusion-mcp.git cd search-fusion-mcp pip install -e .

🌐 Enhanced Proxy Auto-Detection (New in v2.0!)

Search Fusion now features intelligent proxy auto-detection inspired by concurrent-browser-mcp, providing seamless proxy support with zero configuration!

✨ Three-Layer Detection Strategy

  1. Environment Variables - Highest priority, checks HTTP_PROXY, HTTPS_PROXY, ALL_PROXY
  2. Port Scanning - Scans common proxy ports using socket connection testing
  3. System Proxy - Detects OS-level proxy settings (macOS supported)

πŸ” Supported Proxy Ports (Priority Order)

  • 7890 - Clash default port
  • 1087 - V2Ray common port
  • 8080 - Generic HTTP proxy port
  • 3128 - Squid proxy default port
  • 8888 - Other proxy software port
  • 10809 - V2Ray SOCKS port
  • 20171 - Additional proxy port

πŸš€ Zero Configuration Usage

Just run directly - proxy will be auto-detected:

search-fusion-mcp

Manual override (if needed):

env HTTP_PROXY="http://your-proxy:port" search-fusion-mcp

πŸ“Š Detection Process

πŸ” Checking environment variables... πŸ” Scanning proxy ports: [7890, 1087, 8080, ...] βœ… Local proxy port detected: 7890 🌐 Auto-detected proxy: http://127.0.0.1:7890

πŸ†š Comparison with concurrent-browser-mcp

FeatureSearch-Fusionconcurrent-browser-mcp
Detection Methodβœ… Env vars β†’ Port scan β†’ System proxyβœ… Same strategy
Port Listβœ… 7 common portsβœ… 7 common ports
Connection Testβœ… Socket testingβœ… Socket testing
Timeoutβœ… 3 secondsβœ… 3 seconds
macOS Supportβœ… networksetupβœ… networksetup
LanguagePythonTypeScript

MCP Integration

Environment Variable Configuration

Search Fusion uses pure MCP environment variable configuration without requiring config files.

MCP Client Configuration (PyPI Installation):

{ "mcp": { "mcpServers": { "search-fusion": { "command": "search-fusion-mcp", "env": { "GOOGLE_API_KEY": "your_google_api_key", "GOOGLE_CSE_ID": "your_google_cse_id", "SERPER_API_KEY": "your_serper_api_key", "JINA_API_KEY": "your_jina_api_key", "EXA_API_KEY": "your_exa_api_key", "BING_API_KEY": "your_bing_api_key", "BAIDU_API_KEY": "your_baidu_api_key", "BAIDU_SECRET_KEY": "your_baidu_secret_key" } } } } }

MCP Client Configuration (Source Installation):

{ "mcp": { "mcpServers": { "search-fusion": { "command": "python", "args": ["-m", "src.main"], "cwd": "/path/to/your/search-fusion-mcp", "env": { "GOOGLE_API_KEY": "your_google_api_key", "GOOGLE_CSE_ID": "your_google_cse_id", "SERPER_API_KEY": "your_serper_api_key", "JINA_API_KEY": "your_jina_api_key", "EXA_API_KEY": "your_exa_api_key", "BING_API_KEY": "your_bing_api_key", "BAIDU_API_KEY": "your_baidu_api_key", "BAIDU_SECRET_KEY": "your_baidu_secret_key" } } } } }
Supported Environment Variables
Search EngineEnvironment VariableRequiredDescriptionGet API Key
GoogleGOOGLE_API_KEYGOOGLE_CSE_IDBoth neededGoogle Custom Search APIGet API Key
SerperSERPER_API_KEYAPI keySerper Google Search APIGet API Key
Jina AIJINA_API_KEYAPI keyJina AI Search APIGet API Key
BingBING_API_KEYAPI keyMicrosoft Bing Search APIGet API Key
BaiduBAIDU_API_KEYBAIDU_SECRET_KEYBoth neededBaidu Search APIGet API Key
ExaEXA_API_KEYAPI keyExa AI Search APIGet API Key
DuckDuckGoNone required-Free search, no API key needed-

Alternative Variable Names:

# Google GOOGLE_SEARCH_API_KEY # Alternative to GOOGLE_API_KEY GOOGLE_SEARCH_CSE_ID # Alternative to GOOGLE_CSE_ID # Serper SERPER_SEARCH_API_KEY # Alternative to SERPER_API_KEY # Others follow similar pattern...

Engine Priority

Search engines are prioritized automatically:

  1. Google Search (Priority 1) - Premium performance with API key
  2. Serper Search (Priority 1) - Google alternative with advanced features
  3. Jina AI Search (Priority 1.5) - AI-powered search with optional API key for advanced features
  4. DuckDuckGo (Priority 2) - Free, no API key required
  5. Exa Search (Priority 2) - AI-powered search with API key
  6. Bing Search (Priority 3) - Microsoft search API
  7. Baidu Search (Priority 3) - Chinese search engine

πŸ› οΈ MCP Tools

Tools Overview

Perform web searches with intelligent engine selection and failover.

Parameters:

  • query (required): Search query terms
  • num_results (default: 10): Number of results to return
  • engine (default: "auto"): Engine preference
    • "auto": Automatic engine selection (recommended)
    • "google": Prefer Google Search
    • "serper": Prefer Serper Search
    • "jina": Prefer Jina AI Search
    • "duckduckgo": Prefer DuckDuckGo
    • "exa": Prefer Exa Search
    • "bing": Prefer Bing Search
    • "baidu": Prefer Baidu Search

2. fetch_url

Fetch and process web content with intelligent pagination and multi-method fallback.

Parameters:

  • url (required): Web URL to fetch
  • use_jina (default: true): Whether to prioritize Jina Reader for LLM-optimized content
  • with_image_alt (default: false): Whether to generate alt text for images
  • max_length (default: 50000): Maximum content length per page (auto-paginate if exceeded)
  • page_number (default: 1): Retrieve specific page from previously fetched content

Features:

  • Intelligent Multi-Method Fallback: Tries Jina Reader β†’ Serper Scrape β†’ Direct HTTP
  • Automatic Pagination: Splits large content into manageable pages
  • Concurrent-Safe Caching: Unique page IDs prevent conflicts in high-concurrency scenarios
  • LLM-Optimized Content: Clean markdown format optimized for AI processing

3. get_available_engines

Get current status and availability of all search engines.

4. search_wikipedia

Search Wikipedia articles for entities, people, places, concepts, etc.

Parameters:

  • entity (required): Entity to search for
  • first_sentences (default: 10): Number of sentences to return (0 for full content)

5. search_archived_webpage

Search archived versions of websites using Wayback Machine.

Parameters:

  • url (required): Website URL to search
  • year (optional): Target year
  • month (optional): Target month
  • day (optional): Target day

πŸ“– API Examples

# Automatic engine selection result = await search("artificial intelligence trends 2024") # Prefer specific engine result = await search("machine learning", engine="google")

Advanced Web Fetching

# Fetch with intelligent pagination result = await fetch_url("https://example.com/long-article") # If content is paginated, get additional pages if result.get("is_paginated"): page_2 = await get_page(result["page_id"], 2)
# Get Wikipedia summary result = await search_wikipedia("Python programming language") # Get full article result = await search_wikipedia("Quantum computing", first_sentences=0)

πŸ§ͺ Development

Development Setup

git clone https://github.com/sailaoda/search-fusion-mcp.git cd search-fusion-mcp pip install -r requirements.txt pip install -e .

πŸ”§ Configuration Guide

For detailed configuration instructions, see MCP_CONFIG_GUIDE.md.

πŸ“Š Performance

  • Latency: Sub-second response times with caching
  • Availability: 99.9% uptime with intelligent failover
  • Throughput: Handles concurrent requests efficiently
  • Scalability: Efficient resource utilization and concurrent processing

πŸ“ˆ Concurrency Benchmarks

Tested Performance (v3.0.0+):

  • βœ… 50+ concurrent searches - No race conditions or data corruption
  • βœ… Thread-safe statistics - Accurate request counting and error tracking
  • ⚑ Connection pooling - Efficient HTTP resource management
  • πŸ›‘οΈ Timeout protection - 60s per request prevents system overload
  • πŸ“Š Real-time monitoring - Live engine status during high load

Recommended Limits:

  • Concurrent searches: 10 (configurable via semaphore)
  • Connection pool: 100 max connections, 20 keep-alive
  • Request timeout: 60 seconds
  • Memory usage: ~50MB baseline + ~2MB per concurrent request

🀝 Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests for new functionality
  5. Submit a pull request

πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

🚨 Rate Limiting & Best Practices

  • Google Search: 100 queries/day (free tier)
  • Serper API: Varies by plan
  • Jina AI: Rate limits apply based on subscription
  • DuckDuckGo: No official limits, but use responsibly
  • Other engines: Check respective API documentation

Always implement appropriate delays and respect rate limits to ensure sustainable usage.

πŸ“ž Support


Made with ❀️ for the MCP community

Related MCP Servers

  • -
    security
    F
    license
    -
    quality
    An MCP server that integrates with SerpApi to retrieve search results from multiple search engines including Google, Bing, Yahoo, and others, enabling fast access to both live and archived search data.
    Last updated -
    11
  • -
    security
    F
    license
    -
    quality
    An MCP server that enables searching and retrieving content from Confluence documentation systems, providing capabilities for both document searches and full page content retrieval.
    Last updated -
    1
  • -
    security
    A
    license
    -
    quality
    Stores metadata for MCP servers and provides smart search capabilities, allowing users to find appropriate MCP servers for their queries and route requests to the most suitable server.
    Last updated -
    10
    MIT License
  • -
    security
    F
    license
    -
    quality
    An MCP server that implements Retrieval-Augmented Generation to efficiently retrieve and process important information from various sources, providing accurate and contextually relevant responses.
    Last updated -

View all related MCP servers

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sailaoda/search-fusion-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server