If installed via go install, make sure ~/go/bin is in your PATH.
Using with Claude Code (Skills)
This project includes a SKILL.md definition that can be used with Claude Code. This skill provides specialized instructions for Claude to effectively use the web search tools for deep research and fact-checking.
To use it:
Ensure the MCP server is configured in your claude_desktop_config.json (as above).
Structured Output: Properly formatted markdown for AI processing
Content Summarization: Truncates content intelligently at sentence boundaries
Multi-Source: Combines content from multiple search engines
Benefits: Optimized for AI analysis and summarization
Development
Prerequisites
Go 1.21 or higher
Chrome/Chromium browser (for content extraction)
Building
# Build the server
go build -o mcp-websearch-server
# Run tests
go test ./...
# Run tests with coverage
go test -cover ./...
# Format code
go fmt ./...
# Lint (requires golangci-lint)
golangci-lint run
Testing
The project includes comprehensive unit tests with 60%+ coverage:
# Run all tests
go test ./...
# Run with verbose output
go test -v ./...
# Generate coverage report
go test -coverprofile=coverage.out ./...
go tool cover -html=coverage.out
Example Applications
# Test basic search functionality
go run ./examples/basic_search_demo/main.go
# Test hybrid search with content extraction
go run ./examples/hybrid_search_demo/main.go
# Test MCP server tools
go run ./examples/mcp_tools_demo/main.go
How It Works
Search Request: Receives search query via MCP protocol
Engine Selection: Uses goquery-based engines for fast results
Search Execution: Performs HTTP-based search with proper headers
Content Extraction: Uses chromedp for intelligent content extraction
Aggregation: Combines and formats content for AI analysis
Response: Returns structured results via MCP protocol
Search Engine Priority
The hybrid searcher prioritizes engines in this order:
DuckDuckGo - Primary engine (privacy-focused)
Bing - First fallback (comprehensive results)
Brave - Second fallback (independent search)
If one engine fails, the server automatically tries the next available engine.
Error Handling
Implements retry logic with exponential backoff
Graceful fallback to alternative search engines
Structured error messages via MCP protocol
Timeout handling for long-running operations
Rate limiting for content extraction
Performance
Search Speed: ~200-500ms per search using goquery
Content Extraction: ~2-5s per page using chromedp
Concurrent Extraction: Limited to 2-3 simultaneous browser instances
Memory Usage: Optimized with proper context cleanup
Dependencies
MCP Go SDK: Model Context Protocol implementation
chromedp: Browser automation for content extraction
goquery: Fast HTML parsing and scraping
Standard Library: HTTP client, context, sync primitives
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Fragen
Wie installiere ich MCP Websearch Server?
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
Benötigt MCP Websearch Server einen API-Schlüssel?
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Welchen Transport verwendet MCP Websearch Server?
MCP Websearch Server läuft lokal über stdio.
Wann wurde MCP Websearch Server zuletzt geprüft?
Zuletzt geprüft: 2026-10-28. A Model Context Protocol (MCP) server that provides multi-engine web search capabilities with content extraction.