mcp-searxng and one-search-mcp
These are competitors offering overlapping web search capabilities, with A being a specialized wrapper for SearXNG alone while B provides a unified MCP interface supporting multiple search backends (SearXNG, Tavily, DuckDuckGo, Bing) plus web scraping and extraction.
About mcp-searxng
ihor-sokoliuk/mcp-searxng
MCP Server for SearXNG
Exposes two MCP tools: `searxng_web_search` with filtering by time range, language, and safe search level; and `web_url_read` for extracting markdown content with section filtering and paragraph range selection. Implements TTL-based caching for URL content and supports configurable proxy routing per tool, HTTP Basic Auth, and custom User-Agent headers for both search and content extraction interfaces.
About one-search-mcp
yokingma/one-search-mcp
🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.
Implements Model Context Protocol (MCP) server with pluggable search backends (SearXNG, Tavily, DuckDuckGo, Bing, Google, etc.) and exposes four tools—`one_search`, `one_scrape`, `one_map`, `one_extract`—for web search, scraping, and structured data extraction. Uses local browser automation via `agent-browser` for privacy-preserving searches and scraping without external API dependencies, with automatic Chromium detection across Chrome, Edge, and Canary installations. Integrates with Claude Desktop, Cursor, and Windsurf through standard MCP configuration files.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work