brave-search-mcp and one-search-mcp
These two tools are competitors, as both are independent MCP server implementations offering similar comprehensive web search capabilities through various underlying search APIs.
About brave-search-mcp
mikechao/brave-search-mcp
An MCP Server implementation that integrates the Brave Search API, providing, Web Search, Local Points of Interest Search, Image Search, Video Search, News Search and LLM Context Search capabilities
Exposes six distinct search tools through the Model Context Protocol, including a specialized `brave_llm_context_search` function that pre-extracts and tokenizes web content for RAG pipelines with configurable filtering modes. Supports both stdio and HTTP transport modes, with UI widgets for OpenAI Apps and MCP Apps that allow users to selectively control which results get added to model context. Built as an npm package requiring only a Brave Search API key to deploy, with fallback logic (e.g., local search defaults to web search if no location results found) for graceful degradation.
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