wet-mcp and kindly-web-search-mcp-server
One tool is a general-purpose MCP server for web search and content extraction, while the other is a specialized MCP server built on similar principles, focusing on robust content retrieval for AI coding tools and agents.
About wet-mcp
n24q02m/wet-mcp
MCP server for web search, content extraction, and documentation indexing
Provides embedded metasearch (SearXNG) with semantic reranking and query expansion, plus specialized academic research across Google Scholar, arXiv, and PubMed. Features local full-text documentation indexing with HyDE-enhanced retrieval, batch content extraction from up to 50 URLs, and multimodal analysis—all with zero-config local embeddings (Qwen3) or optional cloud providers. Integrates as an MCP server with Claude, Gemini, and Codex via stdio transport, with automatic setup and encrypted credential storage.
About kindly-web-search-mcp-server
Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, etc.). Supports Serper, Tavily, and SearXNG.
Implements MCP (Model Context Protocol) server architecture with stdio transport for seamless integration into AI coding assistants, combining multiple search backends (Serper, Tavily, SearXNG) with specialized parsers for StackExchange, GitHub Issues, arXiv, and Wikipedia that return structured, conversation-complete content. Uses headless Chromium via `nodriver` for real-time webpage extraction into Markdown, eliminating the need for separate web scraping or platform-specific MCP servers. Part of a broader agentic suite designed to improve code quality through integrated tools for semantic navigation, design review, and TDD enforcement.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work